{"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/disp-r-cnn-stereo-3d-object-detection-via","title":"Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation","arxiv_id":"2004.03572","date":"2020-04-07","proceeding":"CVPR 2020 6","authors":["Jiaming Sun","Linghao Chen","Yiming Xie","Siyu Zhang","Qinhong Jiang","Xiaowei Zhou","Hujun Bao"],"abstract":"In this paper, we propose a novel system named Disp R-CNN for 3D object detection from stereo images. Many recent works solve this problem by first recovering a point cloud with disparity estimation and then apply a 3D detector. The disparity map is computed for the entire image, which is costly and fails to leverage category-specific prior. In contrast, we design an instance disparity estimation network (iDispNet) that predicts disparity only for pixels on objects of interest and learns a category-specific shape prior for more accurate disparity estimation. To address the challenge from scarcity of disparity annotation in training, we propose to use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds, which makes our system more widely applicable. Experiments on the KITTI dataset show that, even when LiDAR ground-truth is not available at training time, Disp R-CNN achieves competitive performance and outperforms previous state-of-the-art methods by 20% in terms of average precision.","url_abs":"https://arxiv.org/abs/2004.03572v1","url_pdf":"https://arxiv.org/pdf/2004.03572v1.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":"disp-r-cnn-stereo-3d-object-detection-via","repo_url":"https://github.com/zju3dv/disprcnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"3d-object-detection-from-stereo-images","task_name":"3D Object Detection From Stereo Images"},{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"vehicle-pose-estimation","task_name":"Vehicle Pose Estimation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"disp-r-cnn","method_name":"Disp R-CNN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"disp-r-cnn","name":"Disp R-CNN","full_name":"Disp R-CNN"}],"results":[{"leaderboard":"/sota/3d-object-detection-from-stereo-images-on-1","task":"3D Object Detection From Stereo Images","dataset":"KITTI Cars Moderate","model":"Disp R-CNN","rank_in_archive_order":6,"of":12,"metrics":{"AP75":"45.78"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-from-stereo-images-on-3","task":"3D Object Detection From Stereo Images","dataset":"KITTI Cyclists Moderate","model":"Disp R-CNN","rank_in_archive_order":3,"of":5,"metrics":{"AP50":"24.40"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-from-stereo-images-on-2","task":"3D Object Detection From Stereo Images","dataset":"KITTI Pedestrians Moderate","model":"Disp R-CNN","rank_in_archive_order":3,"of":6,"metrics":{"AP50":"25.80"},"uses_additional_data":false},{"leaderboard":"/sota/vehicle-pose-estimation-on-kitti-cars-hard","task":"Vehicle Pose Estimation","dataset":"KITTI Cars Hard","model":"Disp-RCNN (Stereo)","rank_in_archive_order":14,"of":19,"metrics":{"Average Orientation Similarity":"67.16"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.03572","atlas_url":"https://app.syntology.ai/?focus=2004.03572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03572"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zju3dv/disprcnn","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e12a7703159f2ff5","entry":"filter_bbox_3d","repo":"zju3dv/disprcnn","repo_kind":"official","path":"disprcnn/modeling/pointnet_module/point_rcnn/lib/net/point_rcnn.py","file_url":"https://github.com/zju3dv/disprcnn/blob/HEAD/disprcnn/modeling/pointnet_module/point_rcnn/lib/net/point_rcnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e12a7703159f2ff5"}},{"code_sha256_prefix":"3b1a2015d6936cc4","entry":"remove_empty_proposals","repo":"zju3dv/disprcnn","repo_kind":"official","path":"disprcnn/modeling/pointnet_module/point_rcnn/lib/net/point_rcnn.py","file_url":"https://github.com/zju3dv/disprcnn/blob/HEAD/disprcnn/modeling/pointnet_module/point_rcnn/lib/net/point_rcnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b1a2015d6936cc4"}},{"code_sha256_prefix":"7fa6138ba5e0cabd","entry":"remove_too_right_proposals","repo":"zju3dv/disprcnn","repo_kind":"official","path":"disprcnn/modeling/pointnet_module/point_rcnn/lib/net/point_rcnn.py","file_url":"https://github.com/zju3dv/disprcnn/blob/HEAD/disprcnn/modeling/pointnet_module/point_rcnn/lib/net/point_rcnn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7fa6138ba5e0cabd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}