James Rehg

4 papers University of Illinois at Urbana-Champaign

• Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
• DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images
• Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
• Toward Human Deictic Gesture Target Estimation