ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xinliang, Shi, Yifeng, Wu, Zhenyu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908961962196992
author Wang, Xinliang
Shi, Yifeng
Wu, Zhenyu
author_facet Wang, Xinliang
Shi, Yifeng
Wu, Zhenyu
contents 3D Gaussian Splatting (3DGS) delivers high-fidelity real-time rendering but suffers from geometric and photometric degradations under sparse-view constraints. Current generative restoration approaches are often limited by insufficient temporal coherence, a lack of explicit spatial constraints, and a lack of large-scale training data, resulting in multi-view inconsistencies, erroneous geometric hallucinations, and limited generalization to diverse real-world artifact distributions. In this paper, we present ArtifactWorld, a framework that resolves 3DGS artifact repair through systematic data expansion and a homogeneous dual-model paradigm. To address the data bottleneck, we establish a fine-grained phenomenological taxonomy of 3DGS artifacts and construct a comprehensive training set of 107.5K diverse paired video clips to enhance model robustness. Architecturally, we unify the restoration process within a video diffusion backbone, utilizing an isomorphic predictor to localize structural defects via an artifact heatmap. This heatmap then guides the restoration through an Artifact-Aware Triplet Fusion mechanism, enabling precise, intensity-guided spatio-temporal repair within native self-attention. Extensive experiments demonstrate that ArtifactWorld achieves state-of-the-art performance in sparse novel view synthesis and robust 3D reconstruction. Code and dataset will be made public.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12251
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models
Wang, Xinliang
Shi, Yifeng
Wu, Zhenyu
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) delivers high-fidelity real-time rendering but suffers from geometric and photometric degradations under sparse-view constraints. Current generative restoration approaches are often limited by insufficient temporal coherence, a lack of explicit spatial constraints, and a lack of large-scale training data, resulting in multi-view inconsistencies, erroneous geometric hallucinations, and limited generalization to diverse real-world artifact distributions. In this paper, we present ArtifactWorld, a framework that resolves 3DGS artifact repair through systematic data expansion and a homogeneous dual-model paradigm. To address the data bottleneck, we establish a fine-grained phenomenological taxonomy of 3DGS artifacts and construct a comprehensive training set of 107.5K diverse paired video clips to enhance model robustness. Architecturally, we unify the restoration process within a video diffusion backbone, utilizing an isomorphic predictor to localize structural defects via an artifact heatmap. This heatmap then guides the restoration through an Artifact-Aware Triplet Fusion mechanism, enabling precise, intensity-guided spatio-temporal repair within native self-attention. Extensive experiments demonstrate that ArtifactWorld achieves state-of-the-art performance in sparse novel view synthesis and robust 3D reconstruction. Code and dataset will be made public.
title ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.12251