GaussFlaw-80K and GeoCritic diagnose where 3DGS renderings go wrong, and of what type

arXivarXivPapers

GaussFlaw-80K and GeoCritic diagnose where 3DGS renderings go wrong, and of what type
arXiv / Shaocheng Shen, Zihan Zheng and colleagues

Shaocheng Shen, Zihan Zheng, Kejin Li, Lu Liu, Xiaoyun Zhang, Qiang Hu and Wenjun Zhang introduce GaussFlaw-80K, a dataset for fine-grained perceptual diagnosis of 3D Gaussian Splatting artifacts, with 80,049 artifact regions across 14,289 rendered images, each annotated with a pixel-level mask and one of eight flaw labels spanning geometric, blending and photometric degradations.

Building on the dataset, they propose GeoCritic, a geometry-guided multi-task model that integrates RGB appearance with depth-derived cues to localize artifacts and classify their types. GeoCritic achieves an AUC-J of 0.9507 and Acc@1 of 80.08%, and diagnosis-guided refinement through densification, attribute correction and outlier pruning improves reported global and crop-level metrics across diverse datasets and 3DGS backbones.