Depth Any Video with Scalable Synthetic Data
- URL: http://arxiv.org/abs/2410.10815v1
- Date: Mon, 14 Oct 2024 17:59:46 GMT
- Title: Depth Any Video with Scalable Synthetic Data
- Authors: Honghui Yang, Di Huang, Wei Yin, Chunhua Shen, Haifeng Liu, Xiaofei He, Binbin Lin, Wanli Ouyang, Tong He,
- Abstract summary: 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.
- Score: 98.42356740981839
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse synthetic environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates-even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.
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) - Video Depth without Video Models [34.11454612504574]
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.
arXiv Detail & Related papers (2024-11-28T14:50:14Z) - 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) - xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations [120.52120919834988]
xGen-SynVideo-1 is a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions.
VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens.
DiT model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios.
arXiv Detail & Related papers (2024-08-22T17:55:22Z) - IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation [136.5813547244979]
We present IDOL (unIfied Dual-mOdal Latent diffusion) for high-quality human-centric joint video-depth generation.
Our IDOL consists of two novel designs. First, to enable dual-modal generation and maximize the information exchange between video and depth generation.
Second, to ensure a precise video-depth spatial alignment, we propose a motion consistency loss that enforces consistency between the video and depth feature motion fields.
arXiv Detail & Related papers (2024-07-15T17:36:54Z) - 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.