Jeonghwan Cho, Minsu Kim, Junyoung Hong, Seon Joo Kim (Yonsei University) · Volumetric 3DGS segmentation

The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation

VODA is a plug-and-play supervision objective for segmenting 3D Gaussian Splatting scenes. It groups per-pixel contributors by local depth and supervises all Gaussians in selected depth clusters, so occluded and low-contribution Gaussians are also learned. The authors also introduce Removal-3D, a synthetic object-removal benchmark, and the Removal Depth Error metric, and report consistent gains across four rendering-based baselines on Removal-3D while maintaining performance on LERF and ScanNet.

Open the source ↗

Similar 3D & Spatial releases

  • Budget3D

    Ozgur Kara (BudgetAny project) · Adaptive-budget image-to-3D · Week 47, 2026

  • SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes

    Hao Yu, Zhenwei Wang, Yongzhen Hu, Yuning Gong, Junta Wu, Xiaowei Zhou, Hujun Bao, Tengfei Wang (Zhejiang University) · Gaussian spacing normalisation · Week 47, 2026

  • LucidLyra

    NVIDIA Research (Oliver Hahn, Rodrigo Marcuzzi, Sherwin Bahmani, Jiahui Huang, Laura Leal-Taixé and others) · Queryable 3D scenes · Week 46, 2026

  • L3G-World

    KAIST AI, Ewha Womans University and KAIST Urban AI Institute (Jinhyeok Choi, JoungBin Lee et al.) · Latent Gaussian world model · Week 46, 2026

  • Idol

    Speridlabs (Alejandro Cañada, Chema Garabito) · Image-to-3D splats · Week 45, 2026

  • JST-2

    Viggle AI · World Model · Week 44, 2026

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.