DUSt3R: Geometric 3D Vision Made Easy

• URL: http://arxiv.org/abs/2312.14132v2
• Date: Sat, 26 Oct 2024 12:26:43 GMT
• Title: DUSt3R: Geometric 3D Vision Made Easy
• Authors: Shuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii, Jerome Revaud,
• Abstract summary: We introduce DUSt3R, a novel paradigm for Dense and Unconstrained Stereo 3D Reconstruction of arbitrary image collections. We show that this formulation smoothly unifies the monocular and binocular reconstruction cases. Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera.
• Score: 8.471330244002564
• License:
• Abstract: Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera parameters e.g. intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain, yet they are mandatory to triangulate corresponding pixels in 3D space, which is the core of all best performing MVS algorithms. In this work, we take an opposite stance and introduce DUSt3R, a radically novel paradigm for Dense and Unconstrained Stereo 3D Reconstruction of arbitrary image collections, i.e. operating without prior information about camera calibration nor viewpoint poses. We cast the pairwise reconstruction problem as a regression of pointmaps, relaxing the hard constraints of usual projective camera models. We show that this formulation smoothly unifies the monocular and binocular reconstruction cases. In the case where more than two images are provided, we further propose a simple yet effective global alignment strategy that expresses all pairwise pointmaps in a common reference frame. We base our network architecture on standard Transformer encoders and decoders, allowing us to leverage powerful pretrained models. Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera. Exhaustive experiments on all these tasks showcase that the proposed DUSt3R can unify various 3D vision tasks and set new SoTAs on monocular/multi-view depth estimation as well as relative pose estimation. In summary, DUSt3R makes many geometric 3D vision tasks easy.

Related papers

• Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting [32.66151412557986]
  We present a weak-to-strong eliciting framework aimed at enhancing surround refinement while maintaining robust monocular perception. Our framework employs weakly tuned experts trained on distinct subsets, and each is inherently biased toward specific camera configurations and scenarios. For MC3D-Det joint training, the elaborate dataset merge strategy is designed to solve the problem of inconsistent camera numbers and camera parameters.
  arXiv  Detail & Related papers  (2024-04-10T03:11:10Z)
• Visual Geometry Grounded Deep Structure From Motion [20.203320509695306]
  We propose a new deep pipeline VGGSfM, where each component is fully differentiable and can be trained in an end-to-end manner. First, we build on recent advances in deep 2D point tracking to extract reliable pixel-accurate tracks, which eliminates the need for chaining pairwise matches. We attain state-of-the-art performance on three popular datasets, CO3D, IMC Phototourism, and ETH3D.
  arXiv  Detail & Related papers  (2023-12-07T18:59:52Z)
• 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)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• State of the Art in Dense Monocular Non-Rigid 3D Reconstruction [100.9586977875698]
  3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics. This survey focuses on state-of-the-art methods for dense non-rigid 3D reconstruction of various deformable objects and composite scenes from monocular videos or sets of monocular views.
  arXiv  Detail & Related papers  (2022-10-27T17:59:53Z)
• Monocular 3D Object Detection with Depth from Motion [74.29588921594853]
  We take advantage of camera ego-motion for accurate object depth estimation and detection. Our framework, named Depth from Motion (DfM), then uses the established geometry to lift 2D image features to the 3D space and detects 3D objects thereon. Our framework outperforms state-of-the-art methods by a large margin on the KITTI benchmark.
  arXiv  Detail & Related papers  (2022-07-26T15:48:46Z)
• Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo [71.59494156155309]
  Existing approaches for multi-view 3D pose estimation explicitly establish cross-view correspondences to group 2D pose detections from multiple camera views. We present our multi-view 3D pose estimation approach based on plane sweep stereo to jointly address the cross-view fusion and 3D pose reconstruction in a single shot.
  arXiv  Detail & Related papers  (2021-04-06T03:49:35Z)
• 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.