{"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/pointfusion-deep-sensor-fusion-for-3d","title":"PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation","arxiv_id":"1711.10871","date":"2017-11-29","proceeding":"CVPR 2018 6","authors":["Danfei Xu","Dragomir Anguelov","Ashesh Jain"],"abstract":"We present PointFusion, a generic 3D object detection method that leverages\nboth image and 3D point cloud information. Unlike existing methods that either\nuse multi-stage pipelines or hold sensor and dataset-specific assumptions,\nPointFusion is conceptually simple and application-agnostic. The image data and\nthe raw point cloud data are independently processed by a CNN and a PointNet\narchitecture, respectively. The resulting outputs are then combined by a novel\nfusion network, which predicts multiple 3D box hypotheses and their\nconfidences, using the input 3D points as spatial anchors. We evaluate\nPointFusion on two distinctive datasets: the KITTI dataset that features\ndriving scenes captured with a lidar-camera setup, and the SUN-RGBD dataset\nthat captures indoor environments with RGB-D cameras. Our model is the first\none that is able to perform better or on-par with the state-of-the-art on these\ndiverse datasets without any dataset-specific model tuning.","url_abs":"http://arxiv.org/abs/1711.10871v2","url_pdf":"http://arxiv.org/pdf/1711.10871v2.pdf","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":[{"paper_slug":"pointfusion-deep-sensor-fusion-for-3d","repo_url":"https://github.com/mialbro/PointFusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"pointfusion-deep-sensor-fusion-for-3d","repo_url":"https://github.com/mialbro/pytorch_pointfusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"pointfusion-deep-sensor-fusion-for-3d","repo_url":"https://github.com/mshn2000/PointFusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"6d-pose-estimation","task_name":"6D Pose Estimation using RGB"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"sensor-fusion","task_name":"Sensor Fusion"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1711.10871","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}