DVD: Deterministic Video Depth Estimation with Generative Priors

• URL: http://arxiv.org/abs/2603.12250v1
• Date: Thu, 12 Mar 2026 17:58:06 GMT
• Title: DVD: Deterministic Video Depth Estimation with Generative Priors
• Abstract summary: DVD is the first framework to adapt pre-trained video diffusion models into single-pass depth regressors.<n>DVD achieves state-of-the-art zero-shot performance across benchmarks.<n>We fully release our pipeline, providing the whole training suite for SOTA video depth estimation to benefit the open-source community.
• Score: 87.46576463137801
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing video depth estimation faces a fundamental trade-off: generative models suffer from stochastic geometric hallucinations and scale drift, while discriminative models demand massive labeled datasets to resolve semantic ambiguities. To break this impasse, we present DVD, the first framework to deterministically adapt pre-trained video diffusion models into single-pass depth regressors. Specifically, DVD features three core designs: (i) repurposing the diffusion timestep as a structural anchor to balance global stability with high-frequency details; (ii) latent manifold rectification (LMR) to mitigate regression-induced over-smoothing, enforcing differential constraints to restore sharp boundaries and coherent motion; and (iii) global affine coherence, an inherent property bounding inter-window divergence, which enables seamless long-video inference without requiring complex temporal alignment. Extensive experiments demonstrate that DVD achieves state-of-the-art zero-shot performance across benchmarks. Furthermore, DVD successfully unlocks the profound geometric priors implicit in video foundation models using 163x less task-specific data than leading baselines. Notably, we fully release our pipeline, providing the whole training suite for SOTA video depth estimation to benefit the open-source community.

Related papers

• 3D Consistency Optimization for Self-Supervised Monocular Video Depth Estimation [21.287558280133076]
  We introduce a new paradigm that recasts sequential video depth estimation as an unconstrained multi-view 3D reconstruction problem.<n>Our approach is driven by three constraints: image-level photometric rendering, explicit world-coordinate geometric alignment, and multi-scale temporal gradient consistency.<n>Results show that the proposed approach achieves state-of-the-art spatial accuracy, outperforming the frame-based, video-based depth estimators and the multi-view 3D reconstruction baselines.
  arXiv  Detail & Related papers  (2026-06-14T08:56:45Z)
• Kwai Keye-VL-2.0 Technical Report [53.82434681649277]
  Keye-VL-2.0 is a multimodal foundation model designed to advance long-video understanding and agentic intelligence.<n>It is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures.<n>Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL overcomes the algorithmic dilemma of catastrophic forgetting.
  arXiv  Detail & Related papers  (2026-06-09T09:58:08Z)
• SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere [90.85001795656633]
  Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos.<n>We propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere.
  arXiv  Detail & Related papers  (2026-05-08T16:57:38Z)
• ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes [55.32681167870698]
  Video-informed Pose Spaces (ViPS) is a feed-forward framework that discovers the latent distribution of valid articulations for auto-rigged meshes.<n>ViPS transfers generative video priors into a universal distribution over a given rig parameterization.<n>Our evaluations show that ViPS matches the performance of state-of-the-art methods trained on synthetic artist-created 4D data in both plausibility and diversity.
  arXiv  Detail & Related papers  (2026-04-19T21:21:11Z)
• VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation [34.46015478321541]
  VideoGPA is a data-efficient self-supervised framework to automatically derive dense preference signals.<n>It steers the generative distribution toward inherent 3D consistency without requiring human annotations.<n>It significantly enhances temporal stability, physical plausibility, and motion coherence using minimal preference pairs.
  arXiv  Detail & Related papers  (2026-01-30T18:59:57Z)
• GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors [47.21120442961684]
  We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos.<n>We show that GeometryCrafter achieves state-of-the-art 3D accuracy, temporal consistency, and generalization capability.
  arXiv  Detail & Related papers  (2025-04-01T17:58:03Z)
• Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity [20.86484181698326]
  Existing models, limited to deterministic predictions, overlook real-world multi-layer depth.<n>We introduce a paradigm shift from single-prediction to multi-hypothesis spatial foundation models.
  arXiv  Detail & Related papers  (2025-03-08T02:33:54Z)
• Video Depth without Video Models [34.11454612504574]
  Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame.<n>We show how to turn a single-image latent diffusion model (LDM) into a state-of-the-art video depth estimator.<n>Our model, which we call RollingDepth, has two main ingredients: (i) a multi-frame depth estimator that is derived from a single-image LDM and maps very short video snippets to depth snippets.
  arXiv  Detail & Related papers  (2024-11-28T14:50:14Z)
• Depth Any Video with Scalable Synthetic Data [98.42356740981839]
  We develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse virtual environments.<n>We leverage the powerful priors of generative video diffusion models to handle real-world videos effectively.<n>Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.
  arXiv  Detail & Related papers  (2024-10-14T17:59:46Z)
• NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation [58.21817572577012]
  Video depth estimation aims to infer temporally consistent depth. We introduce NVDS+ that stabilizes inconsistent depth estimated by various single-image models in a plug-and-play manner. We also elaborate a large-scale Video Depth in the Wild dataset, which contains 14,203 videos with over two million frames.
  arXiv  Detail & Related papers  (2023-07-17T17:57:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.