Hi-TOPS, a training-free meso-scale Flow-Freeze prior with TSDF-guided superquadric fitting, achieves competitive 3D part decomposition and the best mIoU on PartNet (55.87).
PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hi-TOPS: Hierarchical Topology-aware Scoring Prior for 3D Part Decomposition
Hi-TOPS, a training-free meso-scale Flow-Freeze prior with TSDF-guided superquadric fitting, achieves competitive 3D part decomposition and the best mIoU on PartNet (55.87).