2019/08/01 by Pingping Zhang, Wei Liu, Zhang, Pingping +7 · 5 citations
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV
paper · pdf · doi:10.48550/arxiv.1908.00382
This work has been accepted as an Oral presentation at ICCV2019, including 10 pages, 6 figures and 6 tables
arxiv created 2019/08/01 · openalex publication_date 2019/08/01 · arxiv updated 2019/08/02 · openalex created_date 2019/08/13 · openalex updated_date 2026/07/28
Semantic Scene Completion (SSC) aims to simultaneously predict the volumetric occupancy and semantic category of a 3D scene. It helps intelligent devices to understand and interact with the surrounding scenes. Due to the high-memory requirement, current methods only produce low-resolution completion predictions, and generally lose the object details. Furthermore, they also ignore the multi-scale spatial contexts, which play a vital role for the 3D inference. To address these issues, in this work we propose a novel deep learning framework, named Cascaded Context Pyramid Network (CCPNet), to jointly infer the occupancy and semantic labels of a volumetric 3D scene from a single depth image. The proposed CCPNet improves the labeling coherence with a cascaded context pyramid. Meanwhile, based on the low-level features, it progressively restores the fine-structures of objects with Guided Residual Refinement (GRR) modules. Our proposed framework has three outstanding advantages: (1) it explicitly models the 3D spatial context for performance improvement; (2) full-resolution 3D volumes are produced with structure-preserving details; (3) light-weight models with low-memory requirements are captured with a good extensibility. Extensive experiments demonstrate that in spite of taking a single-view depth map, our proposed framework can generate high-quality SSC results, and outperforms state-of-the-art approaches on both the synthetic SUNCG and real NYU datasets.