MVOV3D corrects noise in multi-view vision-language features via region-level CLIP encoding, caption-based text features, and geometric pooling, achieving 14.7% mIoU on ScanNet200 and 16.2% on Matterport160 without training 3D networks.
Matterport3d: Learning from rgb-d data in indoor environments
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
-
Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding
MVOV3D corrects noise in multi-view vision-language features via region-level CLIP encoding, caption-based text features, and geometric pooling, achieving 14.7% mIoU on ScanNet200 and 16.2% on Matterport160 without training 3D networks.