PGOV3D reports 59.5 mIoU on ScanNet for open-vocabulary 3D segmentation by pretraining on partial RGB-D views and then fine-tuning on full scenes with self-generated pseudo labels.
Llava-next: Improved reasoning, ocr, and world knowledge,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PGOV3D: Open-Vocabulary 3D Semantic Segmentation with Partial-to-Global Curriculum
PGOV3D reports 59.5 mIoU on ScanNet for open-vocabulary 3D segmentation by pretraining on partial RGB-D views and then fine-tuning on full scenes with self-generated pseudo labels.