arXiv Computer Vision

Gaussians Can Subtract: Neural Dissolve Fields for Hybrid Scene Rendering

Gaussians Can Subtract: Neural Dissolve Fields for Hybrid Scene Rendering proposes a hybrid Mesh‑Gaussian rendering approach that addresses inconsistencies between mesh and Gaussian primitives. The method introduces a subtract‑and‑refill framework called Gaussolve, which selectively dissolves inconsistent mesh content based on a lightweight Neural Dissolve Field and refills the resulting gaps with residual Gaussians. Experiments on structured and semi‑structured scenes show improved visual fidelity, fewer Gaussian primitives, and faster rendering compared to additive hybrids.

Hugging Face Trending Papers
Aug 19

CoMVS-GS: Collaborative Multi-View Stereo and 3D Gaussian Splatting for Surface Reconstruction

CoMVS‑GS is a surface‑reconstruction framework that fuses Multi‑View Stereo (MVS) with 3D Gaussian splatting. It initializes Gaussian primitives from dense MVS points, uses PatchMatch‑3DGS mutual supervision to refine depths and normals, and replaces voxel‑based meshing with a Delaunay graph‑cut pipeline. Experiments on DTU, GauU‑Scene V2, and MatrixCity demonstrate competitive object‑level results and improved geometric accuracy and mesh compactness in outdoor scenes while preserving high rendering quality.

arXiv AI
Sep 28

Spackle: Completing Large View Single Image NVS with Adaptive Gaussians

Spackle is a lightweight residual learning framework designed to improve large-view single-image novel view synthesis (NVS) by mitigating capacity competition in hybrid decoupled systems that combine 3D Gaussian Splatting (3DGS) and diffusion models. It operates in three stages: predicting base 3DGS attributes, automatically identifying poorly reconstructed regions, and learning a residual 3DGS focused on those areas. During inference, Spackle merges the baseline and augmented Gaussians to produce high-fidelity novel views, achieving state‑of‑the‑art performance on large-view-deviation cases.

By Xuanzhi Liu, Yuhe Zhou, Xinyi Wu, Zhenyao Wu, Jinghao Chen, Ruize Han, Song Wang
arXiv Computer Vision
Oct 22

Unfolding 3D Gaussian Splatting via Iterative Gaussian Synopsis

The paper introduces Iterative Gaussian Synopsis, a top‑down unfolding framework that generates compact, progressive levels of detail for 3D Gaussian Splatting (3DGS). Starting from a full‑resolution 3DGS model, it iteratively prunes Gaussian primitives using a learnable mask, building a multi‑level hierarchy that preserves visual quality while reducing storage. The method combines hierarchical spatial grids with a shared Anchor Codebook to capture global structure and local details, enabling efficient, level‑specific rendering with minimal data overhead.

By Yuqin Lu, Yihua Dai, Yang Zhou, Guiqing Li, Shengfeng He
arXiv Computer Vision
Oct 12

CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction

CompactSplat introduces a feedforward scene reconstruction method that adaptively allocates 3D Gaussian primitives based on texture-guided spatial partitioning and hierarchical sampling. By concentrating dense Gaussians in complex regions and using expanded primitives for flat areas, it reduces redundancy and better captures planar geometry. The framework also allows dynamic sparsity control during inference, enabling trade-offs between rendering quality and memory usage without retraining.

By Bing He, Jingnan Gao, Yunuo Chen, Zhengxue Cheng, Rong Xie, Li Song, Wenjun Zhang
arXiv Computer Vision
Sep 18

GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets

GS-PI introduces an optimization‑decoupled framework that transforms Gaussian Splatting (GS) assets into physically based rendering (PBR) compatible Gaussian assets. By treating PBR material generation as a geometry‑conditioned diffusion process on 3D point clouds, it achieves multi‑view consistency and avoids the pixel‑correspondence problems of 2D diffusion. The method employs a multi‑scale cross‑view conditioning mechanism—combining global semantic priors, photometric cues, and spatial view‑direction signals—to prevent specular highlights from baking into intrinsic colors, and then distills the predicted attributes back into a fully relightable PBR‑GS asset without requiring proxy meshes.

By Jieting Xu, Rengan Xie, Zijian Huang, Zehui Jin, Rui Wang, Yuchi Huo