2 papers
cs.CV2025
Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images
Tianhao Wu, Chuanxia Zheng, Frank Guan +2
Most image-based 3D object reconstructors assume that objects are fully visible, ignoring occlusions that commonly occur in real-world scenarios. In this paper, we introduce Amodal…
cs.CV2024
ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decomposition
Tianhao Wu, Chuanxia Zheng, Tat-Jen Cham +1
3D decomposition/segmentation still remains a challenge as large-scale 3D annotated data is not readily available. Contemporary approaches typically leverage 2D machine-generated s…