Pith. sign in

REVIEW 6 minor 1 cited by

Any2Full recovers dense metric depth from any incomplete sensor map by scale-prompting a frozen monocular depth model in one forward pass.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.5

2026-07-15 14:16 UTC pith:W557MKFF

load-bearing objection Clean one-stage scale-prompting of Depth Anything that actually beats two-stage MDE baselines on accuracy, speed, and pattern robustness, with real warehouse numbers to back it.

arxiv 2603.05711 v2 pith:W557MKFF submitted 2026-03-05 cs.CV

Any to Full: Prompting Depth Anything for Depth Completion in One Stage

Zhiyuan Zhou , Ruofeng Liu , Taichi Liu , Weijian Zuo , Shanshan Wang , Zhiqing Hong , Desheng Zhang This is my paper
classification cs.CV
keywords depth completionmonocular depth estimationscale promptingdomain generalizationpattern-agnosticFiLM modulationrobotic perception
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Commodity depth sensors return sparse or gappy maps that break robotic perception. Traditional completion networks overfit both the RGB domain and the exact hole or sparsity pattern they saw in training, while two-stage methods that bolt a monocular depth estimator onto an explicit alignment step add compute and inject structured artifacts. Any2Full instead freezes a strong monocular depth backbone and learns only a lightweight Scale-Aware Prompt Encoder that turns the sparse metric measurements into multi-level scale prompts. These prompts modulate the backbone so its relative depth becomes globally scale-consistent and can be converted to metric depth by a single closed-form fit. The result is a domain-general, pattern-agnostic completer that is both more accurate and faster than prior approaches, already running on warehouse robots that must grasp black packages whose depth is almost entirely missing.

Core claim

Depth completion can be reformulated as a one-stage scale-prompting adaptation of a pretrained monocular depth estimator: sparse metric cues are distilled into unified scale prompts that force the model’s relative output to be globally consistent (alignable by one scale and bias) while leaving its geometric priors intact, thereby achieving domain-general and pattern-agnostic dense metric recovery without intermediate coarse maps or iterative refinement.

What carries the argument

Scale-Aware Prompt Encoder (SAPE): a hierarchical module that first anchors local scale ratios from sparse depth into monocular features via FiLM, then propagates those cues across the scene with geometry-guided attention, finally injecting the resulting multi-level prompts into the monocular decoder so the relative depth becomes scale-consistent.

Load-bearing premise

After simple global normalization that keeps only inter-point scale ratios, the prompt encoder can turn those sparse ratios into multi-level FiLM signals that make the monocular output truly globally consistent rather than still locally warped.

What would settle it

On a held-out scene whose sparse measurements leave large unmeasured regions, compute the variance of local scale factors needed to align the prompted relative depth to ground-truth metric depth; if that variance remains large, the closed-form global fit fails and the one-stage claim collapses.

Watch this falsifier — get emailed when new claim-graph text bears on it.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

0 major / 6 minor

Summary. The paper proposes Any2Full, a one-stage depth completion framework that reformulates the task as scale-prompting adaptation of a frozen pretrained monocular depth estimation (MDE) backbone (Depth Anything v2). A lightweight Scale-Aware Prompt Encoder (SAPE) with Local Enrichment (FiLM coupling of sparse scale cues to MDE features) and Global Propagation (MDE-geometry-guided attention) modules converts normalized sparse depth into multi-level scale prompts that modulate the MDE decoder, producing globally scale-consistent relative depth that is recovered to metric depth by a single closed-form least-squares alignment. The method is trained only on synthetic data with random/hole sampling and claims domain-general, pattern-agnostic performance. Extensive zero-shot experiments across six public datasets, six depth patterns (including unseen Range), three backbone sizes, sparsity/range ablations, module ablations, and a real warehouse robotic grasping deployment support superior average AbsREL (32.2% better than OMNI-DC) and 1.4× speedup versus PriorDA with the same backbone.

Significance. If the empirical claims hold, Any2Full offers a practical new paradigm for universal depth completion: it inherits MDE geometric priors without two-stage coarse-to-fine overhead or iterative test-time optimization, while remaining robust to sensor-induced sparsity, holes, range limits, and domain shifts. The real-world warehouse deployment (grasp success rising from ~28–39% to 91–100% on black packages) and public code/checkpoints strengthen impact for robotics. Strengths include the clean one-stage formulation, direct scale-consistency evidence (Supp. A.1 region-wise maps), progressive module ablations (Tab. 4), attention visualizations, multi-backbone consistency, and efficiency numbers that make the approach deployable. These elements make the work a solid contribution beyond incremental fusion of existing MDE models.

minor comments (6)
  1. Abstract and Sec. 4.2 claim a 32.2% average AbsREL improvement over OMNI-DC; Tab. 1 AVG column shows 0.014 → 0.010 (~28.6%). Clarify the exact averaging procedure (per-pattern relative gains, weighted, etc.).
  2. Fig. 2 caption and diagram contain residual LaTeX artifacts (“Frezze”, “F!”#”, “F+%&%)*” etc.). Clean for camera-ready.
  3. Sec. 3.2 and Supp. C.2: the multi-size patch embedding and masked attention details are useful; a short pseudocode block or diagram inset would improve reproducibility without expanding the main text.
  4. Tab. 1 rank computation (Avg Rank 2.3) is not fully specified (how ties or missing entries are handled). A one-sentence note would suffice.
  5. Fig. 4 and Tab. 3 captions could more explicitly state that Range and extreme sparsity protocols are zero-shot for all methods, reinforcing the pattern-agnostic claim.
  6. Minor notation: the tilde for normalized relative depth is introduced late; define ˜Ds earlier in Sec. 3.1 for readers skimming equations.

Circularity Check

0 steps flagged

No significant circularity; the method is an empirical one-stage architecture whose metric outputs are produced by ordinary network training plus a closed-form post-hoc alignment, not by construction from fitted inputs.

full rationale

Any2Full reformulates depth completion as scale-prompting of a frozen pretrained MDE (Depth Anything v2) via a trainable Scale-Aware Prompt Encoder that produces multi-level FiLM modulators; the final metric map is recovered by non-parametric least-squares alignment of the resulting relative prediction to the sparse measurements (Eq. 1 and Sec. 3.1). The network is trained with standard scale-and-shift-invariant, gradient-matching and anchor losses whose weights are fixed at 0.5 (Sec. 3.3, Supp. C.3); no free parameters are fitted to a subset of the evaluation data and then re-used as “predictions.” Region-wise scale-map analysis (Supp. A.1) and ablations (Tab. 4) supply independent empirical evidence that the prompting step improves global scale consistency, while zero-shot numbers on six public datasets and six depth patterns (Tab. 1) are ordinary external benchmarks. There are no self-definitional equations, no uniqueness theorems imported from the authors’ prior work, and no load-bearing self-citations that reduce the claimed AbsREL gains to a tautology. The derivation chain is therefore self-contained and non-circular.

Axiom & Free-Parameter Ledger

3 free parameters · 4 axioms · 2 invented entities

The central claim rests on the pretrained MDE’s geometric priors, the assumption that global scale/bias alignment becomes sufficient after prompting, ordinary network training hyperparameters, and the newly introduced prompt modules. No new physical constants or unobservable particles are postulated; free parameters are standard ML knobs.

free parameters (3)
  • loss weights λ1–λ4 = 0.5 each
    Set uniformly to 0.5 for Lssi, Lgm, Lanchor, Lr-ssim; chosen by hand rather than cross-validated.
  • learning rate and schedule = 5e-5, 224k steps
    Adam 5e-5 with 10 k warm-up and cosine decay for 224 k steps; standard but free choices that affect final accuracy.
  • number of Global Propagation blocks L and layer indices = L=3 for DA-L
    Aligned to MDE decoder levels (e.g., layers {10,16,22} for ViT-L); design choice that determines how scale cues are diffused.
axioms (4)
  • domain assumption A pretrained relative MDE (Depth Anything v2) already encodes domain-general geometric priors that remain useful after light feature-level modulation.
    Invoked throughout Sec. 1–3; the entire prompting strategy inherits its zero-shot geometry from this assumption.
  • domain assumption After successful scale prompting, residual scale inconsistency is globally constant (single scale + bias) so that non-parametric least-squares recovers metric depth.
    Stated in Sec. 3.1 and quantified in Supp. A.1; if false the one-stage claim fails.
  • domain assumption Synthetic RGB-D pairs with random-point and hole sampling are sufficiently diverse to train a pattern-agnostic prompt encoder that generalizes to real LiDAR, ToF, SfM and range-truncated patterns.
    Training protocol in Sec. 3.3; zero-shot tables rest on this transfer assumption.
  • standard math Standard transformer attention and FiLM layers are well-behaved function approximators for the required scale modulation.
    Used without proof in Eqs. (2)–(4); ordinary deep-learning background.
invented entities (2)
  • Scale-Aware Prompt Encoder (SAPE) with Local Enrichment and Global Propagation modules no independent evidence
    purpose: Convert irregular sparse scale cues into multi-level, pattern-invariant prompts that modulate MDE features.
    Core architectural novelty of the paper; no independent existence outside this work.
  • Unified scale prompt representation obtained by MDE-geometry-guided attention no independent evidence
    purpose: Decouple scale injection from the spatial sampling pattern of the raw depth.
    Defined operationally by the Global Propagation module (Eq. 3); existence is demonstrated only by the paper’s own ablations.

pith-pipeline@v1.1.0-grok45 · 27481 in / 3085 out tokens · 34388 ms · 2026-07-15T14:16:58.820229+00:00 · methodology

0 comments
read the original abstract

Accurate, dense depth estimation is crucial for robotic perception, but commodity sensors often yield sparse or incomplete measurements due to hardware limitations. Existing RGBD-fused depth completion methods learn priors jointly conditioned on training RGB distribution and specific depth patterns, limiting domain generalization and robustness to various depth patterns. Recent efforts leverage monocular depth estimation (MDE) models to introduce domain-general geometric priors, but current two-stage integration strategies relying on explicit relative-to-metric alignment incur additional computation and introduce structured distortions. To this end, we present Any2Full, a one-stage, domain-general, and pattern-agnostic framework that reformulates completion as a scale-prompting adaptation of a pretrained MDE model. To address varying depth sparsity levels and irregular spatial distributions, we design a Scale-Aware Prompt Encoder. It distills scale cues from sparse inputs into unified scale prompts, guiding the MDE model toward globally scale-consistent predictions while preserving its geometric priors. Extensive experiments demonstrate that Any2Full achieves superior robustness and efficiency. It outperforms OMNI-DC by 32.2\% in average AbsREL and delivers a 1.4$\times$ speedup over PriorDA with the same MDE backbone, establishing a new paradigm for universal depth completion. Codes and checkpoints are available at https://github.com/zhiyuandaily/Any2Full.

Figures

Figures reproduced from arXiv: 2603.05711 by Desheng Zhang, Ruofeng Liu, Shanshan Wang, Taichi Liu, Weijian Zuo, Zhiqing Hong, Zhiyuan Zhou.

Figure 1
Figure 1. Figure 1: Depth completion recovers dense depth maps from raw measurements and RGB guidance. (a) Traditional two-stage methods predict coarse depth to bridge the gap be￾tween sparse input and dense output. (b) Recent approaches integrate monocular depth estimation (MDE) to generate relative depth and explicitly align it with sparse depth, disrupting MDE’s geometric priors. (c) Our framework employs a lightweight pro… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the Any2Full. (a) Our framework reformulates depth comple￾tion as a scale-prompting adaptation of a pretrained MDE model. The normalized raw depth is encoded into scale prompts to modulate MDE features for scale-consistent relative depth prediction, followed by a non-parametric least-squares fit to recover the dense metric depth. (b) The Scale-aware Prompt Encoder (SAPE) transforms raw depth in… view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative comparison under various depth sampling patterns. Black shows missing depths, and red boxes mark key areas. Any2Full demonstrates accurate global geometry, structural consistency, and fine-grained detail preservation across all patterns. methods, OMNI-DC and PriorDA appear to overfit to the Sparse setting and generalize poorly to unseen Range patterns, indicating their completion relies heavily… view at source ↗
Figure 4
Figure 4. Figure 4: Robustness comparison on varying depth range. [PITH_FULL_IMAGE:figures/full_fig_p014_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Visualization of scale inconsistency. (a) The backbone MDE (Depth Any￾thing) shows varying regional scale factors when aligned to metric depth (red = larger, blue = smaller), while our prediction yields nearly uniform scales consistent with the ground truth. (b) The bottom row shows the region-partitioned RGB input, sparse depth, and our final result, illustrating how region-wise scales are computed [PITH… view at source ↗
Figure 6
Figure 6. Figure 6: Two-stage methods struggle to correct noisy coarse depths. [PITH_FULL_IMAGE:figures/full_fig_p022_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Visualization of attention propagation from different query points (yellow dots). Each row corresponds to a distinct query location shown in the left column (RGB & query points). The middle and right columns visualize attention maps from two representative heads of the global propagation module in layer 2, illustrating how the propagation extends from nearby to distant regions. Head 1 focuses on refining n… view at source ↗
Figure 8
Figure 8. Figure 8: Robotic warehouse grasping setup and depth results. The table reports grasping success rates across package sizes. Black indicates successful grasps without damage, while red denotes successful but deformed packages due to poor grasp points [PITH_FULL_IMAGE:figures/full_fig_p025_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Examples of black packages used in the warehouse grasping evalua [PITH_FULL_IMAGE:figures/full_fig_p026_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Additional qualitative results on KITTI DC under the Sparse [PITH_FULL_IMAGE:figures/full_fig_p029_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Additional qualitative results on KITTI DC under the Range depth [PITH_FULL_IMAGE:figures/full_fig_p030_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Additional qualitative results on Logistic-Black under the Mixed [PITH_FULL_IMAGE:figures/full_fig_p030_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Additional qualitative results on IBims-1 under the Range depth [PITH_FULL_IMAGE:figures/full_fig_p031_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Additional qualitative results on IBims-1 under the Hole and [PITH_FULL_IMAGE:figures/full_fig_p031_14.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Vision Pretraining for Dense Spatial Perception

    cs.CV 2026-07 conditional novelty 7.0

    A boundary-forcing masked modeling paradigm for self-supervised vision pretraining yields a 1B model rivaling 7B models on dense spatial perception tasks.

Reference graph

Works this paper leans on

71 extracted references · 12 linked inside Pith · cited by 1 Pith paper

  1. [1]

    IEEE Transactions on Pattern Analysis and Ma- chine Intelligence46(4), 2396–2414 (2023)

    Arampatzakis, V., Pavlidis, G., Mitianoudis, N., Papamarkos, N.: Monocular depth estimation: A thorough review. IEEE Transactions on Pattern Analysis and Ma- chine Intelligence46(4), 2396–2414 (2023)

    2023

  2. [2]

    arXiv preprint arXiv:1702.01105 (2017)

    Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2d-3d-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)

    Pith/arXiv arXiv 2017

  3. [3]

    arXiv preprint arXiv:2302.12288 (2023)

    Bhat,S.F.,Birkl,R.,Wofk,D.,Wonka,P.,Müller,M.:Zoedepth:Zero-shottransfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)

    Pith/arXiv arXiv 2023

  4. [4]

    arXiv preprint arXiv:2410.02073 (2024)

    Bochkovskii, A., Delaunoy, A., Germain, H., Santos, M., Zhou, Y., Richter, S.R., Koltun, V.: Depth pro: Sharp monocular metric depth in less than a second. arXiv preprint arXiv:2410.02073 (2024)

    Pith/arXiv arXiv 2024

  5. [5]

    Advances in neural information processing systems33, 1877–1901 (2020)

    Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Nee- lakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language models are few-shot learners. Advances in neural information processing systems33, 1877–1901 (2020)

    1901

  6. [6]

    arXiv preprint arXiv:2001.10773 (2020)

    Cabon, Y., Murray, N., Humenberger, M.: Virtual kitti 2. arXiv preprint arXiv:2001.10773 (2020)

    Pith/arXiv arXiv 2001

  7. [7]

    In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recog- nition

    Chen, P.Y., Liu, A.H., Liu, Y.C., Wang, Y.C.F.: Towards scene understanding: Unsupervised monocular depth estimation with semantic-aware representation. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recog- nition. pp. 2624–2632 (2019)

    2019

  8. [8]

    In: Proceed- ings of the Computer Vision and Pattern Recognition Conference

    Cheng, J., Liu, L., Xu, G., Wang, X., Zhang, Z., Deng, Y., Zang, J., Chen, Y., Cai, Z., Yang, X.: Monster: Marry monodepth to stereo unleashes power. In: Proceed- ings of the Computer Vision and Pattern Recognition Conference. pp. 6273–6282 (2025)

    2025

  9. [9]

    In: Pro- ceedings of the AAAI conference on artificial intelligence

    Cheng, X., Wang, P., Guan, C., Yang, R.: Cspn++: Learning context and resource aware convolutional spatial propagation networks for depth completion. In: Pro- ceedings of the AAAI conference on artificial intelligence. vol. 34, pp. 10615–10622 (2020)

    2020

  10. [10]

    In: Proceedings of the European conference on computer vision (ECCV)

    Cheng, X., Wang, P., Yang, R.: Depth estimation via affinity learned with convo- lutional spatial propagation network. In: Proceedings of the European conference on computer vision (ECCV). pp. 103–119 (2018)

    2018

  11. [11]

    IEEE transactions on pattern analysis and machine intelligence 42(10), 2361–2379 (2019)

    Cheng, X., Wang, P., Yang, R.: Learning depth with convolutional spatial prop- agation network. IEEE transactions on pattern analysis and machine intelligence 42(10), 2361–2379 (2019)

    2019

  12. [12]

    In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)

    Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidi- rectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). pp. 4171–4186 (2019)

    2019

  13. [13]

    arXiv preprint arXiv:2010.11929 (2020)

    Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recogni- tion at scale. arXiv preprint arXiv:2010.11929 (2020)

    Pith/arXiv arXiv 2010

  14. [14]

    Artificial Intelligence Review54(3), 1677–1734 (2021)

    Du, G., Wang, K., Lian, S., Zhao, K.: Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review. Artificial Intelligence Review54(3), 1677–1734 (2021)

    2021

  15. [15]

    Advances in neural information processing systems27 (2014)

    Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems27 (2014)

    2014

  16. [16]

    Communi- cations of the ACM24(6), 381–395 (1981) Abbreviated paper title 17

    Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communi- cations of the ACM24(6), 381–395 (1981) Abbreviated paper title 17

    1981

  17. [17]

    IEEE Sensors Journal11(9), 1917–1926 (2011)

    Foix, S., Alenya, G., Torras, C.: Lock-in time-of-flight (tof) cameras: A survey. IEEE Sensors Journal11(9), 1917–1926 (2011)

    1917

  18. [18]

    In: 2012 IEEE conference on computer vision and pattern recognition

    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE conference on computer vision and pattern recognition. pp. 3354–3361. IEEE (2012)

    2012

  19. [19]

    In: Proceedings of the AAAI Conference on Arti- ficial Intelligence

    Gui, M., Schusterbauer, J., Prestel, U., Ma, P., Kotovenko, D., Grebenkova, O., Baumann, S.A., Hu, V.T., Ommer, B.: Depthfm: Fast generative monocular depth estimation with flow matching. In: Proceedings of the AAAI Conference on Arti- ficial Intelligence. vol. 39, pp. 3203–3211 (2025)

    2025

  20. [20]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Hyoseok, L., Kim, K.S., Byung-Ki, K., Oh, T.H.: Zero-shot depth completion via test-time alignment with affine-invariant depth prior. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 39, pp. 3877–3885 (2025)

    2025

  21. [22]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Jeong, C., Bae, I., Park, J.H., Jeon, H.G.: Test-time prompt tuning for zero-shot depth completion. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 9443–9454 (2025)

    2025

  22. [23]

    In: European conference on computer vision

    Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: European conference on computer vision. pp. 709–727. Springer (2022)

    2022

  23. [24]

    In: Proceedings of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition

    Jun, J., Lee, J.H., Kim, C.S.: Masked spatial propagation network for sparsity- adaptive depth refinement. In: Proceedings of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition. pp. 19768–19778 (2024)

    2024

  24. [25]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recog- nition

    Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Re- purposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recog- nition. pp. 9492–9502 (2024)

    2024

  25. [26]

    arXiv preprint arXiv:1412.6980 (2014)

    Kingma, D.P.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

    Pith/arXiv arXiv 2014

  26. [28]

    In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops

    Koch, T., Liebel, L., Fraundorfer, F., Korner, M.: Evaluation of cnn-based single- image depth estimation methods. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops. pp. 0–0 (2018)

    2018

  27. [29]

    arXiv preprint arXiv:2101.00190 (2021)

    Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)

    Pith/arXiv arXiv 2021

  28. [30]

    In: Proceedings of the Computer Vision and Pattern Recognition Con- ference

    Lin, H., Peng, S., Chen, J., Peng, S., Sun, J., Liu, M., Bao, H., Feng, J., Zhou, X., Kang, B.: Prompting depth anything for 4k resolution accurate metric depth estimation. In: Proceedings of the Computer Vision and Pattern Recognition Con- ference. pp. 17070–17080 (2025)

    2025

  29. [31]

    In: Proceedings of the aaai conference on artificial intelligence

    Lin, Y., Cheng, T., Zhong, Q., Zhou, W., Yang, H.: Dynamic spatial propagation network for depth completion. In: Proceedings of the aaai conference on artificial intelligence. vol. 36, pp. 1638–1646 (2022)

    2022

  30. [32]

    In: European Conference on Computer Vision

    Liu, X., Shao, X., Wang, B., Li, Y., Wang, S.: Graphcspn: Geometry-aware depth completion via dynamic gcns. In: European Conference on Computer Vision. pp. 90–107. Springer (2022)

    2022

  31. [33]

    arXiv preprint arXiv:1608.03983 (2016) 18 Z

    Loshchilov, I., Hutter, F.: Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016) 18 Z. Zhou et al

    Pith/arXiv arXiv 2016

  32. [34]

    arXiv preprint arXiv:2601.22054 (2026)

    Ma, B., Yang, J., Di, D., Zhang, X., Cui, J., Li, H., Xie, Y., Chen, W.: Met- ricanything: Scaling metric depth pretraining with noisy heterogeneous sources. arXiv preprint arXiv:2601.22054 (2026)

    Pith/arXiv arXiv 2026

  33. [35]

    In: 2018 IEEE international conference on robotics and automation (ICRA)

    Ma, F., Karaman, S.: Sparse-to-dense: Depth prediction from sparse depth sam- ples and a single image. In: 2018 IEEE international conference on robotics and automation (ICRA). pp. 4796–4803. IEEE (2018)

    2018

  34. [36]

    Science Robotics4(26), eaau4984 (2019)

    Mahler, J., Matl, M., Satish, V., Danielczuk, M., DeRose, B., McKinley, S., Gold- berg, K.: Learning ambidextrous robot grasping policies. Science Robotics4(26), eaau4984 (2019)

    2019

  35. [37]

    In: 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)

    Maier, D., Hornung, A., Bennewitz, M.: Real-time navigation in 3d environments based on depth camera data. In: 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012). pp. 692–697. IEEE (2012)

    2012

  36. [38]

    arXiv preprint arXiv:2302.13540 (2023)

    Miao, R., Liu, W., Chen, M., Gong, Z., Xu, W., Hu, C., Zhou, S.: Oc- cdepth: A depth-aware method for 3d semantic scene completion. arXiv preprint arXiv:2302.13540 (2023)

    Pith/arXiv arXiv 2023

  37. [39]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Moon, J., Bello, J.L.G., Kwon, B., Kim, M.: From-ground-to-objects: Coarse-to- fine self-supervised monocular depth estimation of dynamic objects with ground contact prior. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 10519–10529 (2024)

    2024

  38. [40]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Park, J.H., Jeong, C., Lee, J., Jeon, H.G.: Depth prompting for sensor-agnostic depth estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 9859–9869 (2024)

    2024

  39. [41]

    In: European conference on computer vision

    Park, J., Joo, K., Hu, Z., Liu, C.K., So Kweon, I.: Non-local spatial propagation network for depth completion. In: European conference on computer vision. pp. 120–136. Springer (2020)

    2020

  40. [42]

    In: Proceedings of the AAAI conference on artificial intelligence

    Perez, E., Strub, F., De Vries, H., Dumoulin, V., Courville, A.: Film: Visual rea- soning with a general conditioning layer. In: Proceedings of the AAAI conference on artificial intelligence. vol. 32 (2018)

    2018

  41. [43]

    IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)

    Piccinelli, L., Sakaridis, C., Yang, Y.H., Segu, M., Li, S., Abbeloos, W., Van Gool, L.: Unidepthv2: Universal monocular metric depth estimation made simpler. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)

    2025

  42. [44]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Piccinelli, L., Yang, Y.H., Sakaridis, C., Segu, M., Li, S., Van Gool, L., Yu, F.: Unidepth: Universal monocular metric depth estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 10106– 10116 (2024)

    2024

  43. [45]

    IEEE transactions on pattern analysis and machine intelligence44(3), 1623–1637 (2020)

    Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE transactions on pattern analysis and machine intelligence44(3), 1623–1637 (2020)

    2020

  44. [46]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Rho, K., Ha, J., Kim, Y.: Guideformer: Transformers for image guided depth com- pletion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6250–6259 (2022)

    2022

  45. [47]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Roberts, M., Ramapuram, J., Ranjan, A., Kumar, A., Bautista, M.A., Paczan, N., Webb, R., Susskind, J.M.: Hypersim: A photorealistic synthetic dataset for holis- tic indoor scene understanding. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 10912–10922 (2021)

    2021

  46. [48]

    In: Proceedings of the IEEE conference on computer vision and pattern recognition

    Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4104–4113 (2016) Abbreviated paper title 19

    2016

  47. [49]

    In: Proceedings of the IEEE conference on computer vision and pattern recognition

    Schops, T., Schonberger, J.L., Galliani, S., Sattler, T., Schindler, K., Pollefeys, M., Geiger, A.: A multi-view stereo benchmark with high-resolution images and multi-camera videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3260–3269 (2017)

    2017

  48. [50]

    In: European conference on computer vision

    Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from rgbd images. In: European conference on computer vision. pp. 746–

  49. [51]

    IEEE Access12, 65041–65057 (2024)

    Tan, P.X., Hoang, D.C., Nguyen, A.N., Nguyen, V.T., Vu, V.D., Nguyen, T.U., Hoang, N.A., Phan, K.T., Tran, D.T., Vu, D.Q., et al.: Attention-based grasp detection with monocular depth estimation. IEEE Access12, 65041–65057 (2024)

    2024

  50. [52]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Tang, J., Tian, F.P., An, B., Li, J., Tan, P.: Bilateral propagation network for depth completion. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 9763–9772 (2024)

    2024

  51. [53]

    IEEE Transactions on Image Processing30, 1116– 1129 (2020)

    Tang, J., Tian, F.P., Feng, W., Li, J., Tan, P.: Learning guided convolutional network for depth completion. IEEE Transactions on Image Processing30, 1116– 1129 (2020)

    2020

  52. [54]

    IEEE Transactions on Neural Networks and Learning Systems 34(12), 9604–9624 (2022)

    Tang, Y., Zhao, C., Wang, J., Zhang, C., Sun, Q., Zheng, W.X., Du, W., Qian, F., Kurths, J.: Perception and navigation in autonomous systems in the era of learning: A survey. IEEE Transactions on Neural Networks and Learning Systems 34(12), 9604–9624 (2022)

    2022

  53. [55]

    In: 2017 international conference on 3D Vision (3DV)

    Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity invariant cnns. In: 2017 international conference on 3D Vision (3DV). pp. 11–20. IEEE (2017)

    2017

  54. [56]

    arXiv preprint arXiv:1908.00463 (2019)

    Vasiljevic, I., Kolkin, N., Zhang, S., Luo, R., Wang, H., Dai, F.Z., Daniele, A.F., Mostajabi, M., Basart, S., Walter, M.R., et al.: Diode: A dense indoor and outdoor depth dataset. arXiv preprint arXiv:1908.00463 (2019)

    Pith/arXiv arXiv 1908

  55. [57]

    In: Pro- ceedings of the IEEE/CVF International Conference on Computer Vision

    Viola, M., Qu, K., Metzger, N., Ke, B., Becker, A., Schindler, K., Obukhov, A.: Marigold-dc: Zero-shot monocular depth completion with guided diffusion. In: Pro- ceedings of the IEEE/CVF International Conference on Computer Vision. pp. 5359–5370 (2025)

    2025

  56. [58]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Wang, H., Xiao, A., Zhang, X., Yang, M., Lu, S.: Pacgdc: Label-efficient generaliz- able depth completion with projection ambiguity and consistency. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 7709–7720 (2025)

    2025

  57. [59]

    IEEE Transactions on Pattern Analysis and Machine Intelligence46(5), 3753–3771 (2023)

    Wang, H., Yang, M., Zheng, N.: G2-monodepth: A general framework of general- ized depth inference from monocular rgb+ x data. IEEE Transactions on Pattern Analysis and Machine Intelligence46(5), 3753–3771 (2023)

    2023

  58. [60]

    IEEE Trans- actions on Pattern Analysis and Machine Intelligence46(11), 7088–7101 (2024)

    Wang, H., Che, Z., Yang, Y., Wang, M., Xu, Z., Qiao, X., Qi, M., Feng, F., Tang, J.: Rdfc-gan: Rgb-depth fusion cyclegan for indoor depth completion. IEEE Trans- actions on Pattern Analysis and Machine Intelligence46(11), 7088–7101 (2024)

    2024

  59. [61]

    In: Proceedings of the ieee/cvf con- ference on computer vision and pattern recognition

    Wang, H., Wang, M., Che, Z., Xu, Z., Qiao, X., Qi, M., Feng, F., Tang, J.: Rgb- depth fusion gan for indoor depth completion. In: Proceedings of the ieee/cvf con- ference on computer vision and pattern recognition. pp. 6209–6218 (2022)

    2022

  60. [62]

    In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

    Wang, W., Zhu, D., Wang, X., Hu, Y., Qiu, Y., Wang, C., Hu, Y., Kapoor, A., Scherer, S.: Tartanair: A dataset to push the limits of visual slam. In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 4909–4916. IEEE (2020)

    2020

  61. [63]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Wang, Y., Li, J., Hong, C., Li, R., Sun, L., Song, X., Wang, Z., Cao, Z., Lin, G.: Tacodepth: Towards efficient radar-camera depth estimation with one-stage fusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 10523–10533 (2025) 20 Z. Zhou et al

    2025

  62. [64]

    arXiv preprint arXiv:2505.10565 (2025)

    Wang, Z., Chen, S., Yang, L., Wang, J., Zhang, Z., Zhao, H., Zhao, Z.: Depth anything with any prior. arXiv preprint arXiv:2505.10565 (2025)

    Pith/arXiv arXiv 2025

  63. [65]

    IEEE Robotics and Automation Letters5(2), 1899–1906 (2020)

    Wong, A., Fei, X., Tsuei, S., Soatto, S.: Unsupervised depth completion from visual inertial odometry. IEEE Robotics and Automation Letters5(2), 1899–1906 (2020)

    1906

  64. [66]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: Un- leashing the power of large-scale unlabeled data. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 10371–10381 (2024)

    2024

  65. [67]

    Advances in Neural Information Processing Systems37, 21875–21911 (2024)

    Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., Zhao, H.: Depth anything v2. Advances in Neural Information Processing Systems37, 21875–21911 (2024)

    2024

  66. [68]

    In: Proceed- ings of the IEEE/CVF international conference on computer vision

    Yin, W., Zhang, C., Chen, H., Cai, Z., Yu, G., Wang, K., Chen, X., Shen, C.: Metric3d: Towards zero-shot metric 3d prediction from a single image. In: Proceed- ings of the IEEE/CVF international conference on computer vision. pp. 9043–9053 (2023)

    2023

  67. [69]

    In: The Fourteenth International Conference on Learning Representations (2026)

    Yu, Z., Zhang, R., Qiu, L., Cao, S.Y., Qiu, K., He, Y., Zhu, S., Dong, Z., Shen, H.l., et al.: Large depth completion model from sparse observations. In: The Fourteenth International Conference on Learning Representations (2026)

    2026

  68. [70]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Zeng, Z., Wang, D., Yang, F., Park, H., Soatto, S., Lao, D., Wong, A.: Wordepth: Variational language prior for monocular depth estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 9708– 9719 (2024)

    2024

  69. [71]

    In: Proceed- ings of the IEEE/CVF conference on computer vision and pattern recognition

    Zhang, Y., Guo, X., Poggi, M., Zhu, Z., Huang, G., Mattoccia, S.: Completion- former: Depth completion with convolutions and vision transformers. In: Proceed- ings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 18527–18536 (2023)

    2023

  70. [72]

    arXiv preprint arXiv:2407.08187 (2024)

    Zhu, R., Wang, C., Song, Z., Liu, L., Zhang, T., Zhang, Y.: Scaledepth: Decom- posing metric depth estimation into scale prediction and relative depth estimation. arXiv preprint arXiv:2407.08187 (2024)

    arXiv 2024

  71. [73]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Zuo,Y.,Yang,W.,Ma,Z.,Deng,J.:Omni-dc:Highlyrobustdepthcompletionwith multiresolution depth integration. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 9287–9297 (2025) Abbreviated paper title 1 Overview This supplementary material provides additional results, implementation details, and analyses. It includes: –Additional ...

    arXiv 2025