Diff-SBSR uses a frozen Stable Diffusion backbone enhanced by multimodal CLIP and BLIP features plus Circle-T loss to outperform prior methods on zero-shot sketch-based 3D shape retrieval benchmarks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MV-HGNN uses hierarchical graph convolutions on multi-view 3D features plus CLIP semantic prototypes to outperform prior methods on sketch-based 3D retrieval in both category-level and zero-shot settings.
citing papers explorer
-
Diff-SBSR: Learning Multimodal Feature-Enhanced Diffusion Models for Zero-Shot Sketch-Based 3D Shape Retrieval
Diff-SBSR uses a frozen Stable Diffusion backbone enhanced by multimodal CLIP and BLIP features plus Circle-T loss to outperform prior methods on zero-shot sketch-based 3D shape retrieval benchmarks.
-
Multi-View Hierarchical Graph Neural Network for Sketch-Based 3D Shape Retrieval
MV-HGNN uses hierarchical graph convolutions on multi-view 3D features plus CLIP semantic prototypes to outperform prior methods on sketch-based 3D retrieval in both category-level and zero-shot settings.