LaRa: Efficient Large-Baseline Radiance Fields

• URL: http://arxiv.org/abs/2407.04699v2
• Date: Mon, 15 Jul 2024 20:18:09 GMT
• Title: LaRa: Efficient Large-Baseline Radiance Fields
• Authors: Anpei Chen, Haofei Xu, Stefano Esposito, Siyu Tang, Andreas Geiger,
• Abstract summary: We propose a method that unifies local and global reasoning in transformer layers, resulting in improved quality and faster convergence. Our model represents scenes as Gaussian Volumes and combines this with an image encoder and Group Attention Layers for efficient feed-forward reconstruction.
• Score: 32.86296116177701
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Radiance field methods have achieved photorealistic novel view synthesis and geometry reconstruction. But they are mostly applied in per-scene optimization or small-baseline settings. While several recent works investigate feed-forward reconstruction with large baselines by utilizing transformers, they all operate with a standard global attention mechanism and hence ignore the local nature of 3D reconstruction. We propose a method that unifies local and global reasoning in transformer layers, resulting in improved quality and faster convergence. Our model represents scenes as Gaussian Volumes and combines this with an image encoder and Group Attention Layers for efficient feed-forward reconstruction. Experimental results demonstrate that our model, trained for two days on four GPUs, demonstrates high fidelity in reconstructing 360 deg radiance fields, and robustness to zero-shot and out-of-domain testing. Our project Page: https://apchenstu.github.io/LaRa/.

Related papers

• DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes [81.56206845824572]
  Novel-view synthesis (NVS) approaches play a critical role in vast scene reconstruction. Few-shot methods often struggle with poor reconstruction quality in vast environments. This paper presents DGTR, a novel distributed framework for efficient Gaussian reconstruction for sparse-view vast scenes.
  arXiv  Detail & Related papers  (2024-11-19T07:51:44Z)
• ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings [48.72040500647568]
  We present ODGS, a novelization pipeline for omnidirectional images, with geometric interpretation. The entire pipeline is parallelized using, achieving optimization and speeds 100 times faster than NeRF-based methods. Results show ODGS restores fine details effectively, even when reconstructing large 3D scenes.
  arXiv  Detail & Related papers  (2024-10-28T02:45:13Z)
• GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation [85.15374487533643]
  We introduce GRM, a large-scale reconstructor capable of recovering a 3D asset from sparse-view images in around 0.1s. GRM is a feed-forward transformer-based model that efficiently incorporates multi-view information. We also showcase the potential of GRM in generative tasks, i.e., text-to-3D and image-to-3D, by integrating it with existing multi-view diffusion models.
  arXiv  Detail & Related papers  (2024-03-21T17:59:34Z)
• Flexible Techniques for Differentiable Rendering with 3D Gaussians [29.602516169951556]
  Neural Radiance Fields demonstrated photorealistic novel view is within reach, but was gated by performance requirements for fast reconstruction of real scenes and objects. We develop extensions to alternative shape representations, in particular, 3D watertight meshes and rendering per-ray normals. These reconstructions are quick, robust, and easily performed on GPU or CPU.
  arXiv  Detail & Related papers  (2023-08-28T17:38:31Z)
• NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support [45.68296352822415]
  We present a method for generating high-quality watertight manifold meshes from multi-view input images. Our method combines the benefits of both worlds; we take the geometry obtained from neural fields, and further optimize the geometry as well as a compact neural texture representation.
  arXiv  Detail & Related papers  (2023-05-26T17:59:21Z)
• Learning to Render Novel Views from Wide-Baseline Stereo Pairs [26.528667940013598]
  We introduce a method for novel view synthesis given only a single wide-baseline stereo image pair. Existing approaches to novel view synthesis from sparse observations fail due to recovering incorrect 3D geometry. We propose an efficient, image-space epipolar line sampling scheme to assemble image features for a target ray.
  arXiv  Detail & Related papers  (2023-04-17T17:40:52Z)
• Neural 3D Reconstruction in the Wild [86.6264706256377]
  We introduce a new method that enables efficient and accurate surface reconstruction from Internet photo collections. We present a new benchmark and protocol for evaluating reconstruction performance on such in-the-wild scenes.
  arXiv  Detail & Related papers  (2022-05-25T17:59:53Z)
• Extracting Triangular 3D Models, Materials, and Lighting From Images [59.33666140713829]
  We present an efficient method for joint optimization of materials and lighting from multi-view image observations. We leverage meshes with spatially-varying materials and environment that can be deployed in any traditional graphics engine.
  arXiv  Detail & Related papers  (2021-11-24T13:58:20Z)
• MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo [52.329580781898116]
  We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images, we propose a generic deep neural network that can reconstruct radiance fields from only three nearby input views via fast network inference.
  arXiv  Detail & Related papers  (2021-03-29T13:15:23Z)

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.