3 papers
cs.CV2024
PT43D: A Probabilistic Transformer for Generating 3D Shapes from Single Highly-Ambiguous RGB Images
Yiheng Xiong, Angela Dai
Generating 3D shapes from single RGB images is essential in various applications such as robotics. Current approaches typically target images containing clear and complete visual d…
cs.CV2023
PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness
Anh-Quan Cao, Angela Dai, Raoul de Charette
We propose the task of Panoptic Scene Completion (PSC) which extends the recently popular Semantic Scene Completion (SSC) task with instance-level information to produce a richer u…
cs.CV2023
DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image
Daoyi Gao, Dávid Rozenberszki, Stefan Leutenegger +1
Perceiving 3D structures from RGB images based on CAD model primitives can enable an effective, efficient 3D object-based representation of scenes. However, current approaches rely…