← Back to all news
arXiv Computer Vision

3DTexMOR: 3D Gaussian Multi-Object Removal via Texture-Space Inpainting

3DTexMOR introduces a method for removing multiple 3D objects from reconstructed scenes by performing texture-space inpainting rather than 2D image inpainting. The approach aggregates observations into shared texture maps, inpaints missing regions, and reprojects the completed maps to supervise Gaussian scene completion, while decomposing appearance to avoid view-dependent artifacts. Experiments show that this technique yields visually plausible results and outperforms existing methods, improving PSNR by 5.8 dB and reducing LPIPS by at least 22%.

Related stories

arXiv AI
Aug 28

CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes

CoGeo-GS is a concept-driven framework for controllable multi-object removal in 3D scenes. It assigns concept-aware semantic tags to 3D Gaussians, allowing flexible object selection and reducing interference between foreground and background within a single optimization stage. The method also introduces a geometry-aware completion pipeline that uses monocular depth priors, diffusion-based refinement, and boundary-aligned blending, along with a geometry-regularized refinement strategy to stabilize reconstruction and preserve multi-view consistency.

By Yuanxiang Ni, Xianliang Huang, Chenhang Ma, Chen Xiao, Yuewen Ma, Ruxin Wang, Hao Zhang
diffusion
More like this →
arXiv Computer Vision
Sep 30

WINGS: Reference-Free Gaussian Splatting Inpainting with 3D-Native Generative Priors

The paper introduces WINGS, a reference‑free Gaussian splatting inpainting technique that operates directly in 3D. It uses a large, pre‑trained 3D generative prior and a structure completion network to reconstruct missing geometry and appearance without generating reference views. The method claims faster performance and reduced multi‑view inconsistency compared to 2D diffusion‑based approaches, and its effectiveness is validated through experiments and a user study.

By No\'e Lallouet, Michael Fischer, Elie Michel
ragdiffusion
More like this →
arXiv Computer Vision
Oct 9

Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement

FreeInpaint is a feed‑forward 3D inpainting framework that reconstructs complete, geometrically consistent scenes directly from unposed multi‑view images with masked regions. It extends a 3D foundation model by propagating masked areas across views, using a Learnable Mask Attention mechanism to maintain reliable cross‑view correspondences and a Support Token Refinement strategy that injects diffusion‑generated auxiliary tokens for high‑fidelity completion. Experiments on diverse datasets show that FreeInpaint delivers superior inpainting quality without requiring pre‑computed camera poses, while maintaining fast inference speed.

By Jingyi Pan, Dan Xu, Qiong Luo
diffusioncomputer-visionefficiency
More like this →
arXiv Computer Vision
Oct 2

DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction

DecomVoxel introduces a guided in‑situ denoising optimization that fuses 3D‑native priors with neural scene reconstruction to improve decompositional scene reconstruction. The method employs an epsilon‑based distillation loss for stable latent refinement and adaptive spatial guidance using occupied and vacant anchors with temporal annealing to reduce hallucinations and spatial drift. Experiments on Replica and ScanNet++ demonstrate that DecomVoxel outperforms state‑of‑the‑art approaches while preserving spatial layout, structural fidelity, and style‑consistent texture, yielding high‑quality textured meshes with clean topology.

By Junfeng Ni, Zirui Zhou, Yixin Chen, Yu Liu, Nan Jiang, Zhifei Yang, Song-Chun Zhu, Siyuan Huang
efficiencybenchmarkssafety
More like this →
arXiv Computer Vision
Sep 16

Bi-FlowGS: Bridging Generative View Completion and Gaussian Geometry through Bidirectional Flow Co-Refinement

Bi-FlowGS introduces a bidirectional co-refinement framework that links generative view completion with 3D Gaussian Splatting geometry. It employs Video-to-Geometry Flow Distillation (V2G) to transfer temporal correspondence from restored videos into Gaussian geometry, mitigating the Geometry Cheating problem. Simultaneously, Geometry-to-Video Flow-Guided Restoration (G2V) uses the current 3DGS geometry to guide temporally consistent video restoration, creating a loop where restored videos and optimized geometry iteratively improve each other, leading to better rendering quality and geometric consistency on wide-baseline and 360° benchmarks.

By Yuetong Wang, Jinsheng Quan, Yi Yang, Yawei Luo
diffusioncomputer-visionefficiencybenchmarks
More like this →
arXiv Computer Vision
Sep 22

D3GS: Depth, DINO, and RGB Diffusion Co-Guided 3D Gaussian Splatting for Sparse-View Reconstruction

arXiv:2609.22941v1 Announce Type: new Abstract: Novel view synthesis from sparse inputs remains challenging for 3D Gaussian Splatting (3DGS) due to ambiguous geometry, cross-view inconsistency, and m...

By Yunqi Gao, Zhanfeng Liao, Hanzhang Tu, Zhaoqi Su, Guoqing Zheng, Songtao Wang, Hongwen Zhang, Zhou Xue, Leyuan Liu, Yebin Liu
llmsdiffusionbenchmarks
More like this →
arXiv Computer Vision
Aug 27

Compact Feed-Forward 3D Gaussians via Saliency-Guided Primitive Merging

The paper introduces a structure‑aware merging pipeline that consolidates per‑pixel 3D Gaussian primitives from any feed‑forward reconstruction method into a compact, content‑adaptive Gaussian set. By grouping spatially coherent Gaussians with adaptive superpixel segmentation guided by a saliency map, compressing clusters via a learned encoder, and merging representations across views using geometric overlap and feature similarity, the method reduces the number of Gaussians to about one‑twentieth of the original while preserving visual quality. A level‑of‑detail decoder allows controllable resolution, and the pipeline operates as a backbone‑agnostic post‑processing module, improving robustness and rendering efficiency.

By Tim-Felix Fassch, Jochen Kall, Cyrill Stachniss
computer-vision
More like this →