Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing
- URL: http://arxiv.org/abs/2403.10050v1
- Date: Fri, 15 Mar 2024 06:42:55 GMT
- Title: Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing
- Authors: Tian-Xing Xu, Wenbo Hu, Yu-Kun Lai, Ying Shan, Song-Hai Zhang,
- Abstract summary: 3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering.
We propose a novel approach, namely Texture-GS, to disentangle the appearance from the geometry by representing it as a 2D texture mapped onto the 3D surface.
Our method not only facilitates high-fidelity appearance editing but also achieves real-time rendering on consumer-level devices.
- Score: 79.10630153776759
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering. However, it couples the appearance and geometry of the scene within the Gaussian attributes, which hinders the flexibility of editing operations, such as texture swapping. To address this issue, we propose a novel approach, namely Texture-GS, to disentangle the appearance from the geometry by representing it as a 2D texture mapped onto the 3D surface, thereby facilitating appearance editing. Technically, the disentanglement is achieved by our proposed texture mapping module, which consists of a UV mapping MLP to learn the UV coordinates for the 3D Gaussian centers, a local Taylor expansion of the MLP to efficiently approximate the UV coordinates for the ray-Gaussian intersections, and a learnable texture to capture the fine-grained appearance. Extensive experiments on the DTU dataset demonstrate that our method not only facilitates high-fidelity appearance editing but also achieves real-time rendering on consumer-level devices, e.g. a single RTX 2080 Ti GPU.
Related papers
- 3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering [8.59572577251833]
We propose a novel regularization method using the gradients of a signed distance function estimated from the Gaussians.
We demonstrate the effectiveness of our approach on datasets such as Mip-NeRF360, Tanks and Temples, and Deep-Blending.
arXiv Detail & Related papers (2025-01-14T18:40:33Z) - GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction [79.42244344704154]
GausSurf employs geometry guidance from multi-view consistency in texture-rich areas and normal priors in texture-less areas of a scene.
Our method surpasses state-of-the-art methods in terms of reconstruction quality and computation time.
arXiv Detail & Related papers (2024-11-29T03:54:54Z) - TCLC-GS: Tightly Coupled LiDAR-Camera Gaussian Splatting for Autonomous Driving [14.80202289008908]
Most 3D Gaussian Splatting (3D-GS) based methods for urban scenes initialize 3D Gaussians directly with 3D LiDAR points.
We design a novel LiDAR-Camera Gaussian Splatting (TCLC-GS) to fully leverage the combined strengths of both LiDAR and camera sensors.
Our method demonstrates fast training and achieves real-time RGB and depth rendering at 90 FPS in resolution of 1920x1280 (Waymo) and 120 FPS in resolution of 1600x900 (nuScenes) in urban scenarios.
arXiv Detail & Related papers (2024-04-03T02:26:15Z) - UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling [71.87807614875497]
We propose UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures.
We collect and process a new dataset of human motion, which includes multi-view images, scanned models, parametric model registration, and corresponding texture maps. Experimental results demonstrate that our method achieves state-of-the-art synthesis of novel view and novel pose.
arXiv Detail & Related papers (2024-03-18T09:03:56Z) - Hybrid Explicit Representation for Ultra-Realistic Head Avatars [55.829497543262214]
We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time.
UV-mapped 3D mesh is utilized to capture sharp and rich textures on smooth surfaces, while 3D Gaussian Splatting is employed to represent complex geometric structures.
Experiments that our modeled results exceed those of state-of-the-art approaches.
arXiv Detail & Related papers (2024-03-18T04:01:26Z) - Nuvo: Neural UV Mapping for Unruly 3D Representations [61.87715912587394]
Existing UV mapping algorithms operate on geometry produced by state-of-the-art 3D reconstruction and generation techniques.
We present a UV mapping method designed to operate on geometry produced by 3D reconstruction and generation techniques.
arXiv Detail & Related papers (2023-12-11T18:58:38Z) - AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis [78.17671694498185]
We propose AUV-Net which learns to embed 3D surfaces into a 2D aligned UV space.
As a result, textures are aligned across objects, and can thus be easily synthesized by generative models of images.
The learned UV mapping and aligned texture representations enable a variety of applications including texture transfer, texture synthesis, and textured single view 3D reconstruction.
arXiv Detail & Related papers (2022-04-06T21:39:24Z)
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.