CVPR2025

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Wenbo Hu, Xiangjun Gao, Xiaoyu Li, Sijie Zhao, Xiaodong Cun, Yong Zhang, Long Quan, Ying Shan

摘要

https://depthcrafter.github.io Input video Depth-Anything-V2 Ours Time Figure 1. We innovate DepthCrafter, a novel video depth estimation approach, that can generate temporally consistent long depth sequences with fine-grained details for open-world videos, without requiring additional information such as camera poses or optical flow.