CRAG: Can 3D Generative Models Help 3D Assembly?
Researchers have developed CRAG, a novel approach to 3D assembly that integrates generative modeling with pose estimation. Unlike previous methods that solely focus on rigid transformations, CRAG treats assembly and shape generation as mutually reinforcing processes. This allows CRAG to synthesize plausible complete shapes and predict part poses, even when some pieces are missing, achieving state-of-the-art performance on in-the-wild objects. AI
IMPACT This research advances 3D reconstruction by combining generative models with assembly, potentially improving applications in robotics and computer vision.