SOTAVerified

Zero-shot 3D classification

Papers

Showing 110 of 16 papers

TitleStatusHype
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding0
MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding0
OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned ImagesCode1
TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding0
ShapeLLM: Universal 3D Object Understanding for Embodied InteractionCode3
MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition0
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-trainingCode1
Uni3D: Exploring Unified 3D Representation at ScaleCode2
ViT-Lens: Initiating Omni-Modal Exploration through 3D InsightsCode1
Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D RepresentationCode1
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.