Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis

• URL: http://arxiv.org/abs/2410.22817v2
• Date: Thu, 31 Oct 2024 07:07:27 GMT
• Title: Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis
• Authors: Zhiyuan Min, Yawei Luo, Jianwen Sun, Yi Yang,
• Abstract summary: Generalizable 3DGS can reconstruct new scenes from sparse-view observations in a feed-forward inference manner. Existing methods rely heavily on epipolar priors, which can be unreliable in complex realworld scenes. We propose eFreeSplat, an efficient feed-forward 3DGS-based model for generalizable novel view synthesis.
• Score: 25.924727931514735
• License:
• Abstract: Generalizable 3D Gaussian splitting (3DGS) can reconstruct new scenes from sparse-view observations in a feed-forward inference manner, eliminating the need for scene-specific retraining required in conventional 3DGS. However, existing methods rely heavily on epipolar priors, which can be unreliable in complex realworld scenes, particularly in non-overlapping and occluded regions. In this paper, we propose eFreeSplat, an efficient feed-forward 3DGS-based model for generalizable novel view synthesis that operates independently of epipolar line constraints. To enhance multiview feature extraction with 3D perception, we employ a selfsupervised Vision Transformer (ViT) with cross-view completion pre-training on large-scale datasets. Additionally, we introduce an Iterative Cross-view Gaussians Alignment method to ensure consistent depth scales across different views. Our eFreeSplat represents an innovative approach for generalizable novel view synthesis. Different from the existing pure geometry-free methods, eFreeSplat focuses more on achieving epipolar-free feature matching and encoding by providing 3D priors through cross-view pretraining. We evaluate eFreeSplat on wide-baseline novel view synthesis tasks using the RealEstate10K and ACID datasets. Extensive experiments demonstrate that eFreeSplat surpasses state-of-the-art baselines that rely on epipolar priors, achieving superior geometry reconstruction and novel view synthesis quality. Project page: https://tatakai1.github.io/efreesplat/.

Related papers

• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images [100.80376573969045]
  NoPoSplat is a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from multi-view images. Our model achieves real-time 3D Gaussian reconstruction during inference. This work makes significant advances in pose-free generalizable 3D reconstruction and demonstrates its applicability to real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-31T17:58:22Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction [46.269350101349715]
  HiSplat is a novel framework for generalizable 3D Gaussian Splatting. It generates hierarchical 3D Gaussians via a coarse-to-fine strategy. It significantly enhances reconstruction quality and cross-dataset generalization.
  arXiv  Detail & Related papers  (2024-10-08T17:59:32Z)
• Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs [29.669534899109028]
  We introduce Splatt3R, a pose-free, feed-forward method for in-the-wild 3D reconstruction and novel view synthesis from stereo pairs. Given uncalibrated natural images, Splatt3R can predict 3D Gaussian Splats without requiring any camera parameters or depth information. Splatt3R can reconstruct scenes at 4FPS at 512 x 512 resolution, and the resultant splats can be rendered in real-time.
  arXiv  Detail & Related papers  (2024-08-25T18:27:20Z)
• FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes [50.534213038479926]
  FreeSplat is capable of reconstructing geometrically consistent 3D scenes from long sequence input towards free-view synthesis. We propose a simple but effective free-view training strategy that ensures robust view synthesis across broader view range regardless of the number of views.
  arXiv  Detail & Related papers  (2024-05-28T08:40:14Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting [58.41056963451056]
  We propose a few-shot view synthesis framework based on 3D Gaussian Splatting. This framework enables real-time and photo-realistic view synthesis with as few as three training views. FSGS achieves state-of-the-art performance in both accuracy and rendering efficiency across diverse datasets.
  arXiv  Detail & Related papers  (2023-12-01T09:30:02Z)
• GS-IR: 3D Gaussian Splatting for Inverse Rendering [71.14234327414086]
  We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) We extend GS, a top-performance representation for novel view synthesis, to estimate scene geometry, surface material, and environment illumination from multi-view images captured under unknown lighting conditions. The flexible and expressive GS representation allows us to achieve fast and compact geometry reconstruction, photorealistic novel view synthesis, and effective physically-based rendering.
  arXiv  Detail & Related papers  (2023-11-26T02:35:09Z)
• Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields [28.549053233615382]
  Generalizable NeRF can synthesize novel views across new scenes, eliminating the need for scene-specific retraining in vanilla NeRF. We propose an Entangled View-Epipolar Information aggregation method dubbed EVE-NeRF.
  arXiv  Detail & Related papers  (2023-11-20T15:35:00Z)

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.