GAP3D is a diffusion-based alignment technique that maps VLM latents to dense patch embeddings from image encoders, enabling modular VLM conditioning for 3D generation without 3D training data.
ISBN 978-3-031-73234-8
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GAP3D: Generative Alignment of VLM Latents to Patch-Level Embeddings for 3D Generation
GAP3D is a diffusion-based alignment technique that maps VLM latents to dense patch embeddings from image encoders, enabling modular VLM conditioning for 3D generation without 3D training data.