SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2411.06390v2
• Date: Tue, 12 Nov 2024 06:41:21 GMT
• Title: SplatFormer: Point Transformer for Robust 3D Gaussian Splatting
• Authors: Yutong Chen, Marko Mihajlovic, Xiyi Chen, Yiming Wang, Sergey Prokudin, Siyu Tang,
• Abstract summary: 3D Gaussian Splatting (3DGS) has recently transformed photorealistic reconstruction, achieving high visual fidelity and real-time performance. rendering quality significantly deteriorates when test views deviate from the camera angles used during training, posing a major challenge for applications in immersive free-viewpoint rendering and navigation. We introduce SplatFormer, the first point transformer model specifically designed to operate on Gaussian splats. Our model significantly improves rendering quality under extreme novel views, achieving state-of-the-art performance in these challenging scenarios and outperforming various 3DGS regularization techniques, multi-scene models tailored for sparse view synthesis, and diffusion
• Score: 18.911307036504827
• License:
• Abstract: 3D Gaussian Splatting (3DGS) has recently transformed photorealistic reconstruction, achieving high visual fidelity and real-time performance. However, rendering quality significantly deteriorates when test views deviate from the camera angles used during training, posing a major challenge for applications in immersive free-viewpoint rendering and navigation. In this work, we conduct a comprehensive evaluation of 3DGS and related novel view synthesis methods under out-of-distribution (OOD) test camera scenarios. By creating diverse test cases with synthetic and real-world datasets, we demonstrate that most existing methods, including those incorporating various regularization techniques and data-driven priors, struggle to generalize effectively to OOD views. To address this limitation, we introduce SplatFormer, the first point transformer model specifically designed to operate on Gaussian splats. SplatFormer takes as input an initial 3DGS set optimized under limited training views and refines it in a single forward pass, effectively removing potential artifacts in OOD test views. To our knowledge, this is the first successful application of point transformers directly on 3DGS sets, surpassing the limitations of previous multi-scene training methods, which could handle only a restricted number of input views during inference. Our model significantly improves rendering quality under extreme novel views, achieving state-of-the-art performance in these challenging scenarios and outperforming various 3DGS regularization techniques, multi-scene models tailored for sparse view synthesis, and diffusion-based frameworks.

Related papers

• 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)
• 3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors [13.191199172286508]
  Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos. 3DGS-Enhancer is a novel pipeline for enhancing the representation quality of 3DGS representations.
  arXiv  Detail & Related papers  (2024-10-21T17:59:09Z)
• Dense Point Clouds Matter: Dust-GS for Scene Reconstruction from Sparse Viewpoints [9.069919085326]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in scene synthesis and novel view synthesis tasks. In this study, we present Dust-GS, a novel framework specifically designed to overcome the limitations of 3DGS in sparse viewpoint conditions.
  arXiv  Detail & Related papers  (2024-09-13T07:59:15Z)
• TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers [14.708092244093665]
  We develop a strategy that utilizes a predicted depth confidence map to guide accurate local feature matching. We present a novel G-3DGS method named TranSplat, which obtains the best performance on both the RealEstate10K and ACID benchmarks.
  arXiv  Detail & Related papers  (2024-08-25T08:37:57Z)
• WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections [8.261637198675151]
  Novel View Synthesis (NVS) from unconstrained photo collections is challenging in computer graphics. We propose an efficient point-based differentiable rendering framework for scene reconstruction from photo collections. Our approach outperforms existing approaches on the rendering quality of novel view and appearance synthesis with high converge and rendering speed.
  arXiv  Detail & Related papers  (2024-06-04T15:17:37Z)
• LP-3DGS: Learning to Prune 3D Gaussian Splatting [71.97762528812187]
  We propose learning-to-prune 3DGS, where a trainable binary mask is applied to the importance score that can find optimal pruning ratio automatically. Experiments have shown that LP-3DGS consistently produces a good balance that is both efficient and high quality.
  arXiv  Detail & Related papers  (2024-05-29T05:58:34Z)
• 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)
• Bootstrap 3D Reconstructed Scenes from 3D Gaussian Splatting [10.06208115191838]
  We present a bootstrapping method to enhance the rendering of novel views using trained 3D-GS. Our results indicate that bootstrapping effectively reduces artifacts, as well as clear enhancements on the evaluation metrics.
  arXiv  Detail & Related papers  (2024-04-29T12:57:05Z)
• SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior [53.52396082006044]
  Current methods struggle to maintain rendering quality at the viewpoint that deviates significantly from the training viewpoints. This issue stems from the sparse training views captured by a fixed camera on a moving vehicle. We propose a novel approach that enhances the capacity of 3DGS by leveraging prior from a Diffusion Model.
  arXiv  Detail & Related papers  (2024-03-29T09:20:29Z)
• GaussianPro: 3D Gaussian Splatting with Progressive Propagation [49.918797726059545]
  3DGS relies heavily on the point cloud produced by Structure-from-Motion (SfM) techniques. We propose a novel method that applies a progressive propagation strategy to guide the densification of the 3D Gaussians. Our method significantly surpasses 3DGS on the dataset, exhibiting an improvement of 1.15dB in terms of PSNR.
  arXiv  Detail & Related papers  (2024-02-22T16:00:20Z)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)

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.