View-Dependent 3DGS

3DGS: 3D Gaussian Splatting

Follow this topic Ask about this topic

Latest papers

10 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Gaussians Can Subtract: Neural Dissolve Fields for Hybrid Scene Rendering
Nov 4, 2026Yiyan Wang, Haohan Liu, Tetsuo Shibuya3D Scene Representation Neural Rendering
The University of Tokyo, Japan · Fuzhou University, China
3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields
Nov 2, 2026Yixiao Yang, Yu-Shen Liu, Zhizhong Han3DGS Training Novel View Synthesis
School of Software, Tsinghua University, Beijing, China · Department of Computer Science, Wayne State University, Detroit, USA
Remote Sensing Sparse-View 3D Gaussian Splatting via Depth Image-Based Rendering
Sep 28, 2026Jiaming Kang, Zhengxia Zou, Zhenwei Shi3D Gaussian Splatting 3D Reconstruction
Beihang University
GSPotential: Camera Potential Field for Sparse-View 3D Gaussian Splatting
Aug 29, 2026Zeyuan An, Yanghang Xiao, Zhiying Leng +2View-Dependent 3DGS 3D Gaussian Splatting
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China · School of Computer Science and Engineering, Beihang University, Beijing, China · Zhongguancun Laboratory, Beijing, China
UniqueSplat: View-conditioned 3D Gaussian Splatting for Generalizable 3D Reconstruction
Aug 3, 2026Haixu Song, Xiaoke Yang, Shengjun Zhang +23D Gaussian Splatting Novel View Synthesis
Tsinghua University, China
Improving Sparse-View 3DGS Generalization via Flat Minima Optimization
Jul 1, 2026Kangmin Seo, Sangeek Hyun, MinKyu Lee +13D Gaussian Splatting Novel View Synthesis
Sungkyunkwan University, South Korea
TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
May 21, 2026Hyeseong Kim, Geonhui Son, Deukhee Lee +13D Gaussian Splatting Novel View Synthesis
Yonsei University · Korea Institute of Science and Technology
ViewSplat: View-Adaptive 3D Gaussian Splatting for Feed-Forward Synthesis
Mar 26, 2026Moonyeon Jeong, Seunggi Min, Suhyeon Lee +13D Gaussian Splatting Novel View Synthesis
University of Seoul · Korea Electronics Technology Institute
Pose-Free Omnidirectional Gaussian Splatting for 360-Degree Videos with Consistent Depth Priors
Mar 24, 2026Chuanqing Zhuang, Xin Lu, Zehui Deng +4View-Dependent 3DGS 3D Gaussian Splatting
School of Artificial Intelligence, University of Chinese Academy of Sciences · Chongqing University · Air Force Engineering University
HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse Views
Mar 1, 2026Jiashu Li, Xumeng Han, Zhaoyang Wei +5View-Dependent 3DGS 3D Gaussian Splatting
University of the Chinese Academy of Sciences

Nov 4, 2026J/K move · Enter open · S save

Gaussians Can Subtract: Neural Dissolve Fields for Hybrid Scene Rendering

Yiyan Wang, Haohan Liu, Tetsuo Shibuya

The University of Tokyo, Japan · Fuzhou University, China

3D Scene Representation Neural Rendering 3D Gaussian Splatting View-Dependent 3DGS Differentiable Rendering

Open paper AskPDF arXiv

Hybrid Mesh-Gaussian rendering combines compact textured surfaces with flexible 3D Gaussian primitives, offering an efficient alternative to purely Gaussian scene representations for structured environments. Existing scene-reconstruction hybrids commonly follow an additive formulation, where Gaussian residuals compensate for errors left by the mesh. However, not every Mesh-Gaussian conflict is caused by missing content: residual geometry errors, occlusion mismatch, texture-projection artifacts, and view-dependent appearance can make the same mesh content consistent in one view but inconsistent in another. We therefore formulate hybrid rendering as a multi-view inconsistency problem and present Gaussolve, a subtract-and-refill framework that selectively dissolves inconsistent mesh content before residual Gaussians refill the revealed regions. We introduce a lightweight Neural Dissolve Field, parameterized by scalar spherical-harmonic Gaussians, to learn where and from which viewing directions mesh content should be dissolved. A continuous transmittance fusion rule progressively exposes residual Gaussians behind the dissolved mesh, preserving their reconstruction gradients and avoiding hard visibility discontinuities. Experiments on structured and semi-structured scenes demonstrate higher visual fidelity with fewer Gaussian primitives and faster rendering. Project page: https://ooosn.github.io/gaussians-can-subtract/