Pith. sign in

REVIEW 5 cited by

DepthFM: Fast Monocular Depth Estimation with Flow Matching

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.13788 v2 pith:XQFBSHKZ submitted 2024-03-20 cs.CV

classification cs.CV
keywords depthmodelwhiledataestimationgenerativeimageperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth estimation as a direct transport between image and depth distributions. We are the first to explore flow matching in this field, and we demonstrate that its interpolation trajectories enhance both training and sampling efficiency while preserving high performance. While generative models typically require extensive training data, we mitigate this dependency by integrating external knowledge from a pre-trained image diffusion model, enabling effective transfer even across differing objectives. To further boost our model performance, we employ synthetic data and utilize image-depth pairs generated by a discriminative model on an in-the-wild image dataset. As a generative model, our model can reliably estimate depth confidence, which provides an additional advantage. Our approach achieves competitive zero-shot performance on standard benchmarks of complex natural scenes while improving sampling efficiency and only requiring minimal synthetic data for training.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Dens3R: A Foundation Model for 3D Geometry Prediction

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Dens3R jointly regresses pointmaps, depth, normals, and image matching from unposed images using a two-stage transformer training with normal-based intrinsic invariance.

  2. E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    E3D-Bench compares 16 3D geometric foundation models on depth, reconstruction, pose, and view-synthesis tasks with a unified evaluation toolkit.

  3. UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Fine-tuning a pretrained video diffusion transformer to predict geometry in one shared global frame produces consistent, camera-free surface normals and coordinates across entire video clips.

  4. Region-aware Depth Scale Adaptation with Sparse Measurements

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A non-learning method segments an image and gives each region its own scale and shift, fitted to a few sparse depth points, to turn relative monocular depth predictions into metric depth more accurately than a single ...

  5. M3Depth: Wavelet-Enhanced Depth Estimation on Mars via Mutual Boosting of Dual-Modal Data

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A wavelet-enhanced stereo network that combines low-frequency feature preservation with depth-normal consistency reports lower depth error than prior stereo models on a synthetic Mars dataset, with qualitative success...

Pith tools