Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

arXiv:2501.12375 · cs.CV, cs.AI · Submitted 2025-01-21 · Read on arXiv

cs.CV, cs.AI

Submitted: 2025-01-21

Updated: 2026-10-14

Comments: Project page: https://videodepthanything.github.io/

Project page: https://videodepthanything.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Temporal consistency — 1× in this paper · explained in 3 episodes

Sources

• ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
• MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• Virtual KITTI 2
• DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
• WildAvatar: Learning In-the-wild 3D Avatars from the Web
• Decoupled Weight Decay Regularization
• DINOv2: Learning Robust Visual Features without Supervision
• ControlNeXt: Powerful and Efficient Control for Image and Video Generation
• Learning Temporally Consistent Video Depth from Video Diffusion Priors
• Depth Any Video with Scalable Synthetic Data
• Depth Anything V2
• ControlVideo: Training-free Controllable Text-to-Video Generation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models