SOTAVerified

Zero-shot 3D classification

Papers

Showing 116 of 16 papers

TitleStatusHype
ShapeLLM: Universal 3D Object Understanding for Embodied InteractionCode3
Uni3D: Exploring Unified 3D Representation at ScaleCode2
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world LearningCode2
ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D UnderstandingCode2
ULIP-2: Towards Scalable Multimodal Pre-training for 3D UnderstandingCode2
OpenShape: Scaling Up 3D Shape Representation Towards Open-World UnderstandingCode2
ViT-Lens: Initiating Omni-Modal Exploration through 3D InsightsCode1
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingCode1
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-trainingCode1
OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned ImagesCode1
PointCLIP: Point Cloud Understanding by CLIPCode1
Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D RepresentationCode1
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding0
TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding0
MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition0
MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding0
Show:102550

No leaderboard results yet.