VODA: depth-clustered volumetric supervision fixes incomplete 3D Gaussian segmentation
yonseiworld · hf · 2026-11-20
Yonsei University researchers identify a flaw in 3D Gaussian Splatting segmentation: methods trained and evaluated on rendered views concentrate alpha-blended feature supervision on dominant contributors, leaving occluded or low-contribution Gaussians unsupervised — rendered masks can look accurate while 3D segmentation is incomplete.
- VODA is a plug-and-play supervision objective that exploits local depth structure to group per-pixel contributors and directly supervise all Gaussians in selected depth clusters, bypassing contribution-weighted gradient delivery
- The paper also introduces Removal-3D, a synthetic object-removal benchmark, and Removal Depth Error (RDE) to evaluate volumetric completeness
More from Research
- DeepSeek ramps up game designer hiring, fueling game-training rumor — teortaxesTex · 2026-11-20
- ICLR 2027 desk-rejects papers after reviewers fail to file AI-use disclosure forms — algo_diver · 2026-11-20
- Chorus paper: shared n-gram tables cut memory 87% while beating DeepSeek's Engram — brown2green · 2026-11-20
- Synthetic benchmarks for concept bottleneck models isolate failure modes, NeurIPS 2026 — berkustun · 2026-11-20
- Inhabitant: training-free LLM agent completes 74/75 long-horizon household tasks — Yao Zhang · 2026-11-20
- EPFL team unveils unified 3D generative model for structure-based drug design and docking — HannesStaerk · 2026-11-20