3 accepted papers
We introduce PixARMesh, a method to autoregressively reconstruct complete 3D indoor scene meshes directly from a single RGB image. Unlike prior methods that rely on implicit signed distance fields and post-hoc layout optimization, PixARMesh jointly predicts object layout and geometry within a unifie
This paper tackles the challenge of robust reconstruction, i.e., the task of reconstructing a 3D scene from a set of inconsistent multi-view images. Some recent works have attempted to simultaneously remove image inconsistencies and perform reconstruction by integrating image degradation modeling in…
Flexible proximity sensors mounted on robot arms boost obstacle detection in human-robot collaboration (HRC). However, most of the flexible sensor placements lack further analysis to exploit the flexibility, leading to an inefficient and overpriced sensing system. In this work, we propose a systemat