Pith. sign in

REVIEW 10 cited by

Depth Any Video with Scalable Synthetic Data

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 2410.10815 v2 pith:OUK4W4KC submitted 2024-10-14 cs.CV cs.AI

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

Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse virtual environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates-even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency. The code and model weights are open-sourced.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Unified Video Dense Prediction from Disjoint Data

    cs.CV 2026-07 conditional novelty 7.0 of 10

    A single video backbone predicts eight dense scene tasks from separate single-task datasets via latent distillation from diffusion-based specialists, with no co-annotated data or pseudo-labels.

  2. Forget, Anticipate and Adapt: Test Time Training for Long Videos

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    FFN performs TTT on multi-hour videos by restricting updates to three frames and using a surprise metric for adaptive window sizing, plus a new EpicTours dataset.

  3. GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion

    cs.CV 2025-05 conditional novelty 7.0 of 10

    GeoMan predicts temporally consistent depth and normals for human videos by conditioning an image-to-video diffusion model on first-frame geometry and using a root-relative depth representation.

  4. Video Generation Models are General-Purpose Vision Learners

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A video-diffusion backbone fine-tuned as a single-step multi-task perceiver matches or beats specialists on depth, normals, pose and segmentation, with high data efficiency and sim-to-real transfer.

  5. Towards Consistent Video Geometry Estimation

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    ViGeo is a feed-forward transformer for video geometry that introduces dynamic chunking attention and a completion-based data refinement framework to achieve SOTA on depth, normals, and point map estimation.

  6. Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Vid-CamEdit re-synthesizes monocular videos along user-defined camera paths by conditioning a video diffusion model on 2D flows derived from estimated 3D geometry, without training on multi-view video data.

  7. 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.

  8. Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Concatenating monocular depth maps as an extra input channel improves video instance segmentation and reaches 56.2 AP, a new state of the art on OVIS.

  9. DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A training-free diffusion-guidance framework that couples scale alignment across windows and geometric multi-view constraints inside the denoising loop yields more scale- and geometry-consistent depth for long videos.

  10. Reconstructing 4D Spatial Intelligence: A Survey

    cs.CV 2025-07 accept novelty 4.0 of 10

    A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.

Pith tools