Pith. sign in

REVIEW 8 cited by

Learning Temporally Consistent Video Depth from Video Diffusion Priors

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 2406.01493 v4 pith:HCFYXUNL submitted 2024-06-03 cs.CV

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

This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal in fostering temporal consistency. Therefore, we reformulate depth prediction into a conditional generation problem to provide contextual information within a clip and across clips. Specifically, we propose a consistent context-aware training and inference strategy for arbitrarily long videos to provide cross-clip context. We sample independent noise levels for each frame within a clip during training while using a sliding window strategy and initializing overlapping frames with previously predicted frames without adding noise. Moreover, we design an effective training strategy to provide context within a clip. Extensive experimental results validate our design choices and demonstrate the superiority of our approach, dubbed ChronoDepth. Project page: https://xdimlab.github.io/ChronoDepth/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. 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.

  2. Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Hallo4D uses vision-language models to detect and correct spatial and temporal mistakes in AI-generated 3D and 4D content, improving consistency without retraining the base generators.

  3. 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.

  4. 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.

  5. 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.

  6. 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.

  7. LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion

    cs.CV 2025-07 conditional novelty 5.0 of 10

    LangScene-X generates RGB, normal, and semantic videos from sparse views to reconstruct 3D language-embedded Gaussian fields that support open-ended text queries.

  8. 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