Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos

• URL: http://arxiv.org/abs/2412.09621v1
• Date: Thu, 12 Dec 2024 18:59:54 GMT
• Title: Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
• Authors: Linyi Jin, Richard Tucker, Zhengqi Li, David Fouhey, Noah Snavely, Aleksander Holynski,
• Abstract summary: We present a system for mining high-quality 4D reconstructions from internet stereoscopic, wide-angle videos. We use this method to generate large-scale data in the form of world-consistent, pseudo-metric 3D point clouds. We demonstrate the utility of this data by training a variant of DUSt3R to predict structure and 3D motion from real-world image pairs.
• Score: 76.07894127235058
• License:
• Abstract: Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly supervising methods for recovering 3D motion remains challenging due to the fundamental difficulty of obtaining ground truth annotations. We present a system for mining high-quality 4D reconstructions from internet stereoscopic, wide-angle videos. Our system fuses and filters the outputs of camera pose estimation, stereo depth estimation, and temporal tracking methods into high-quality dynamic 3D reconstructions. We use this method to generate large-scale data in the form of world-consistent, pseudo-metric 3D point clouds with long-term motion trajectories. We demonstrate the utility of this data by training a variant of DUSt3R to predict structure and 3D motion from real-world image pairs, showing that training on our reconstructed data enables generalization to diverse real-world scenes. Project page: https://stereo4d.github.io

Related papers

• DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos [76.01906393673897]
  We propose a self-supervised method to jointly learn 3D motion and depth from monocular videos. Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion. Our model delivers superior performance in all evaluated settings.
  arXiv  Detail & Related papers  (2024-03-09T12:22:46Z)
• R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras [106.52409577316389]
  R3D3 is a multi-camera system for dense 3D reconstruction and ego-motion estimation. Our approach exploits spatial-temporal information from multiple cameras, and monocular depth refinement. We show that this design enables a dense, consistent 3D reconstruction of challenging, dynamic outdoor environments.
  arXiv  Detail & Related papers  (2023-08-28T17:13:49Z)
• AutoDecoding Latent 3D Diffusion Models [95.7279510847827]
  We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations.
  arXiv  Detail & Related papers  (2023-07-07T17:59:14Z)
• FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow [26.528667940013598]
  Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. Key challenge preventing the deployment of these 3D scene learners on large-scale video data is their dependence on precise camera poses from structure-from-motion. We propose a method that jointly reconstructs camera poses and 3D neural scene representations online and in a single forward pass.
  arXiv  Detail & Related papers  (2023-05-31T20:58:46Z)
• 3D Data Augmentation for Driving Scenes on Camera [50.41413053812315]
  We propose a 3D data augmentation approach termed Drive-3DAug, aiming at augmenting the driving scenes on camera in the 3D space. We first utilize Neural Radiance Field (NeRF) to reconstruct the 3D models of background and foreground objects. Then, augmented driving scenes can be obtained by placing the 3D objects with adapted location and orientation at the pre-defined valid region of backgrounds.
  arXiv  Detail & Related papers  (2023-03-18T05:51:05Z)
• Learning 3D Scene Priors with 2D Supervision [37.79852635415233]
  We propose a new method to learn 3D scene priors of layout and shape without requiring any 3D ground truth. Our method represents a 3D scene as a latent vector, from which we can progressively decode to a sequence of objects characterized by their class categories. Experiments on 3D-FRONT and ScanNet show that our method outperforms state of the art in single-view reconstruction.
  arXiv  Detail & Related papers  (2022-11-25T15:03:32Z)
• YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection [6.5702792909006735]
  YOLOStereo3D is trained on one single GPU and runs at more than ten fps. It demonstrates performance comparable to state-of-the-art stereo 3D detection frameworks without usage of LiDAR data.
  arXiv  Detail & Related papers  (2021-03-17T03:43:54Z)
• Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation [57.11299763566534]
  We present a solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. We exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points. Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections.
  arXiv  Detail & Related papers  (2020-04-05T12:52:29Z)

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.