Gerard Pons-Moll
2 papers · Latest:
Computer Vision
GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers
GeoRelight introduces a Multi-Modal Diffusion Transformer for joint 3D geometry reconstruction and relighting from a single image, improving physical consistency.
2604.20715
Computer VisionInHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement
InHabit leverages 2D image foundation models to automatically generate large-scale, photorealistic 3D human-scene interaction data, improving embodied AI training.
2604.19673
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.