Video Depth without Video Models

• URL: http://arxiv.org/abs/2411.19189v1
• Date: Thu, 28 Nov 2024 14:50:14 GMT
• Title: Video Depth without Video Models
• Authors: Bingxin Ke, Dominik Narnhofer, Shengyu Huang, Lei Ke, Torben Peters, Katerina Fragkiadaki, Anton Obukhov, Konrad Schindler,
• Abstract summary: Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame. We show how to turn a single-image latent diffusion model (LDM) into a state-of-the-art video depth estimator. 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.
• Score: 34.11454612504574
• License:
• Abstract: Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame. Recent advances in single-image depth estimation, brought about by the rise of large foundation models and the use of synthetic training data, have fueled a renewed interest in video depth. However, naively applying a single-image depth estimator to every frame of a video disregards temporal continuity, which not only leads to flickering but may also break when camera motion causes sudden changes in depth range. An obvious and principled solution would be to build on top of video foundation models, but these come with their own limitations; including expensive training and inference, imperfect 3D consistency, and stitching routines for the fixed-length (short) outputs. We take a step back and demonstrate how to turn a single-image latent diffusion model (LDM) into a state-of-the-art video depth estimator. 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 (typically frame triplets) to depth snippets. (ii) a robust, optimization-based registration algorithm that optimally assembles depth snippets sampled at various different frame rates back into a consistent video. RollingDepth is able to efficiently handle long videos with hundreds of frames and delivers more accurate depth videos than both dedicated video depth estimators and high-performing single-frame models. Project page: rollingdepth.github.io.

Related papers

• Video Depth Anything: Consistent Depth Estimation for Super-Long Videos [60.857723250653976]
  We propose Video Depth Anything for high-quality, consistent depth estimation in super-long videos. Our model is trained on a joint dataset of video depth and unlabeled images, similar to Depth Anything V2. Our approach sets a new state-of-the-art in zero-shot video depth estimation.
  arXiv  Detail & Related papers  (2025-01-21T18:53:30Z)
• Align3R: Aligned Monocular Depth Estimation for Dynamic Videos [50.28715151619659]
  We propose a novel video-depth estimation method called Align3R to estimate temporal consistent depth maps for a dynamic video. Our key idea is to utilize the recent DUSt3R model to align estimated monocular depth maps of different timesteps. Experiments demonstrate that Align3R estimates consistent video depth and camera poses for a monocular video with superior performance than baseline methods.
  arXiv  Detail & Related papers  (2024-12-04T07:09:59Z)
• Depth Any Video with Scalable Synthetic Data [98.42356740981839]
  We develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse synthetic environments. We leverage the powerful priors of generative video diffusion models to handle real-world videos effectively. 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)
• DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos [51.90501863934735]
  We present DepthCrafter, a method for generating temporally consistent long depth sequences with intricate details for open-world videos. The generalization ability to open-world videos is achieved by training the video-to-depth model from a pre-trained image-to-video diffusion model. Our training approach enables the model to generate depth sequences with variable lengths at one time, up to 110 frames, and harvest both precise depth details and rich content diversity from realistic and synthetic datasets.
  arXiv  Detail & Related papers  (2024-09-03T17:52:03Z)
• 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)
• Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth [90.33296913575818]
  In some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency. We propose a locally weighted linear regression method to recover the scale and shift with very sparse anchor points. Our method can boost the performance of existing state-of-the-art approaches by 50% at most over several zero-shot benchmarks.
  arXiv  Detail & Related papers  (2022-02-03T08:52:54Z)

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.