Metraipolis › archive › dc_fc9e499ae08a
GaussFlaw: Fine-Grained Perceptual Diagnosis for 3D Gaussian Splatting — arXiv:2611.02767
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02767
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:55:09.045Z
- SHA-256 of the archived text
6f486c1719f17cc19e75eaac55c43034d169ec9d5ad54763a77d8112c1d3a7e9- Stable URL of this page
https://metraipolis.com/documento/dc_fc9e499ae08a
How to cite
GaussFlaw: Fine-Grained Perceptual Diagnosis for 3D Gaussian Splatting — arXiv:2611.02767 — arXiv (en), https://arxiv.org/abs/2611.02767 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc9e499ae08a (Metraipolis archive dc_fc9e499ae08a, sha256 6f486c1719f17cc19e75eaac55c43034d169ec9d5ad54763a77d8112c1d3a7e9)
BibTeX
@misc{dcfc9e499ae08a,
title = {GaussFlaw: Fine-Grained Perceptual Diagnosis for 3D Gaussian Splatting — arXiv:2611.02767},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02767},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc9e499ae08a; sha256 6f486c1719f17cc19e75eaac55c43034d169ec9d5ad54763a77d8112c1d3a7e9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02767. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
3D Gaussian Splatting (3DGS) enables photorealistic novel- view synthesis with real-time rendering, yet fine-grained di- agnosis of its rendering artifacts remains challenging. These artifacts are typically spatially localized and exhibit diverse degradation patterns, making them difficult to character- ize using global quality metrics and image-level assessment benchmarks, which provide no explicit indication of where they occur or what types of artifacts they represent. To ad- dress this limitation, we introduce GaussFlaw-80K, the first large-scale dataset for fine-grained perceptual diagnosis in 3DGS. Constructed through a model-assisted human-in-the- loop pipeline, GaussFlaw-80K contains 80,049 artifact re- gions across 14,289 rendered images, each annotated with a pixel-level mask and one of eight flaw labels spanning ge- ometric, blending, and photometric degradations. These an- notations turn 3DGS artifact diagnosis into an explicit and measurable task. Building on this dataset, we propose Ge- oCritic, a geometry-guided multi-task model that integrates RGB appearance with depth-derived cues to jointly localize artifacts and classify their flaw types. Beyond evaluation, we further demonstrate the downstream benefits of fine-grained diagnosis through three complementary targeted operations: Gaussian densification, attribute correction, and outlier prun- ing. Experiments show that GeoCritic achieves an AUC-J of 0.9507 and an Acc@1 of 80.08%, while diagnosis-guided re- finement improves all reported global and crop-level metrics across diverse datasets and 3DGS backbones. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.02767 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:16:53.022Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).