3 papers
cs.CV2025
GARF: Learning Generalizable 3D Reassembly for Real-World Fractures
Sihang Li, Zeyu Jiang, Grace Chen +9
3D reassembly is a challenging spatial intelligence task with broad applications across scientific domains. While large-scale synthetic datasets have fueled promising learning-base…
cs.CV2024
Adversarial Exploitation of Data Diversity Improves Visual Localization
Sihang Li, Siqi Tan, Bowen Chang +3
Visual localization, which estimates a camera's pose within a known scene, is a fundamental capability for autonomous systems. While absolute pose regression (APR) methods have sho…
cs.RO2024
FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction
Irving Fang, Kairui Shi, Xujin He +7
Humans effortlessly integrate common-sense knowledge with sensory input from vision and touch to understand their surroundings. Emulating this capability, we introduce FusionSense,…