{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/up-to-down-network-fusing-multi-scale-context","title":"Up-to-Down Network: Fusing Multi-Scale Context for 3D Semantic Scene Completion","arxiv_id":null,"date":"2021-09-27","proceeding":"IEEE International Workshop on Intelligent Robots and Systems (IROS) 2021 9","authors":["Hao Zou","Xuemeng Yang","Tianxin Huang","Chujuan Zhang","Yong liu","Wanlong Li","Feng Wen","Hongbo Zhang"],"abstract":"An efficient 3D scene perception algorithm is a vital component for autonomous driving and robotics systems. In this paper, we focus on semantic scene completion, which is a task of jointly estimating the volumetric occupancy and semantic labels of objects. Since the real-world data is sparse and occluded, this is an extremely challenging task. We propose a novel framework, named Up-to-Down network (UDNet), to achieve the large-scale semantic scene completion with an encoder-decoder architecture for voxel grids. The novel up-to-down block can effectively aggregate multi-scale context information to improve labeling coherence, and the atrous spatial pyramid pooling module is leveraged to expand the receptive field while preserving detailed geometric information. Besides, the proposed multi-scale fusion mechanism efficiently aggregates global background information and improves the semantic completion accuracy. Moreover, to further satisfy the needs of different tasks, our UDNet can accomplish the multi-resolution semantic completion, achieving faster but coarser completion. Detailed experiments in the semantic scene completion benchmark of SemanticKITTI illustrate that our proposed framework surpasses the state-of-the-art methods with remarkable margins and a real-time inference speed by using only voxel grids as input.","url_abs":"https://ieeexplore.ieee.org/abstract/document/9635888","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9635888","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"3d-semantic-scene-completion","task_name":"3D Semantic Scene Completion"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"decoder","task_name":"Decoder"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"pyramid-pooling-module","method_name":"Pyramid Pooling Module"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"spatial-pyramid-pooling","method_name":"Spatial Pyramid Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-scene-completion-on-semantickitti","task":"3D Semantic Scene Completion","dataset":"SemanticKITTI","model":"UDNet","rank_in_archive_order":7,"of":20,"metrics":{"mIoU":"19.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}