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.

Original post →

More from Research

Research channel →