{"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/objects-are-different-flexible-monocular-3d","title":"Objects are Different: Flexible Monocular 3D Object Detection","arxiv_id":"2104.02323","date":"2021-04-06","proceeding":"CVPR 2021 1","authors":["Yunpeng Zhang","Jiwen Lu","Jie zhou"],"abstract":"The precise localization of 3D objects from a single image without depth information is a highly challenging problem. Most existing methods adopt the same approach for all objects regardless of their diverse distributions, leading to limited performance for truncated objects. In this paper, we propose a flexible framework for monocular 3D object detection which explicitly decouples the truncated objects and adaptively combines multiple approaches for object depth estimation. Specifically, we decouple the edge of the feature map for predicting long-tail truncated objects so that the optimization of normal objects is not influenced. Furthermore, we formulate the object depth estimation as an uncertainty-guided ensemble of directly regressed object depth and solved depths from different groups of keypoints. Experiments demonstrate that our method outperforms the state-of-the-art method by relatively 27\\% for the moderate level and 30\\% for the hard level in the test set of KITTI benchmark while maintaining real-time efficiency. Code will be available at \\url{https://github.com/zhangyp15/MonoFlex}.","url_abs":"https://arxiv.org/abs/2104.02323v1","url_pdf":"https://arxiv.org/pdf/2104.02323v1.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":"objects-are-different-flexible-monocular-3d","repo_url":"https://github.com/zhangyp15/MonoFlex","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"objects-are-different-flexible-monocular-3d","repo_url":"https://github.com/yanglei18/mix-teaching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"objects-are-different-flexible-monocular-3d","repo_url":"https://github.com/Owen-Liuyuxuan/visualDet3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-3d-object-detection","task_name":"Monocular 3D Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-3d-object-detection-on-kitti-cars","task":"Monocular 3D Object Detection","dataset":"KITTI Cars Moderate","model":"MonoFLEX","rank_in_archive_order":9,"of":29,"metrics":{"AP Medium":"13.89"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.02323","atlas_url":"https://app.syntology.ai/?focus=2104.02323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02323"}},"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/yanglei18/mix-teaching","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Owen-Liuyuxuan/visualDet3D","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhangyp15/MonoFlex","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":7,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":5,"ran":2,"repositories":1},"listed":{"samples":15,"ran":9,"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":"570e350e7fe7526b","entry":"ClipBoxes","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"570e350e7fe7526b"}},{"code_sha256_prefix":"c5197ebb950e466e","entry":"IoULoss","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c5197ebb950e466e"}},{"code_sha256_prefix":"8e7a3c3289cb3e80","entry":"MonoFlexHead","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e7a3c3289cb3e80"}},{"code_sha256_prefix":"59022d9630576578","entry":"_nms","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59022d9630576578"}},{"code_sha256_prefix":"af38ff2bb862b433","entry":"boxes3d_to_bev_torch","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af38ff2bb862b433"}},{"code_sha256_prefix":"6cbf46794989b731","entry":"cat","repo":"zhangyp15/MonoFlex","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/zhangyp15/MonoFlex/blob/HEAD/model/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6cbf46794989b731"}},{"code_sha256_prefix":"65d7a40d70c53ed9","entry":"compute_bin_loss","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"65d7a40d70c53ed9"}},{"code_sha256_prefix":"7df13fb9e54d592b","entry":"compute_res_loss","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7df13fb9e54d592b"}},{"code_sha256_prefix":"74be68131587e23b","entry":"decode_depth_from_keypoints","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74be68131587e23b"}},{"code_sha256_prefix":"4bf22db9eaf70901","entry":"decode_depth_inv_sigmoid","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4bf22db9eaf70901"}},{"code_sha256_prefix":"5a951495ac113177","entry":"strip_prefix_if_present","repo":"zhangyp15/MonoFlex","repo_kind":"official","path":"utils/model_serialization.py","file_url":"https://github.com/zhangyp15/MonoFlex/blob/HEAD/utils/model_serialization.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a951495ac113177"}},{"code_sha256_prefix":"7b2125261c5b536d","entry":"KM3DHead","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7b2125261c5b536d"}},{"code_sha256_prefix":"8469c42e1fc712db","entry":"Position_loss","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8469c42e1fc712db"}},{"code_sha256_prefix":"03b36f268d8645d0","entry":"_topk_channel","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03b36f268d8645d0"}},{"code_sha256_prefix":"65a16c264996059d","entry":"affine_transform","repo":"zhangyp15/MonoFlex","repo_kind":"official","path":"model/heatmap_coder.py","file_url":"https://github.com/zhangyp15/MonoFlex/blob/HEAD/model/heatmap_coder.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65a16c264996059d"}},{"code_sha256_prefix":"a7fa48606189776e","entry":"boxes_iou3d_gpu","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7fa48606189776e"}},{"code_sha256_prefix":"9d749234d255406c","entry":"compute_rot_loss","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9d749234d255406c"}},{"code_sha256_prefix":"c044d44b5a7087e4","entry":"gaussian_radius","repo":"zhangyp15/MonoFlex","repo_kind":"official","path":"model/heatmap_coder.py","file_url":"https://github.com/zhangyp15/MonoFlex/blob/HEAD/model/heatmap_coder.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c044d44b5a7087e4"}},{"code_sha256_prefix":"dae0c091d06a2048","entry":"gen_position","repo":"Owen-Liuyuxuan/visualDet3D","repo_kind":"listed","path":"visualDet3D/networks/heads/monoflex_head.py","file_url":"https://github.com/Owen-Liuyuxuan/visualDet3D/blob/HEAD/visualDet3D/networks/heads/monoflex_head.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dae0c091d06a2048"}},{"code_sha256_prefix":"194052ec40659a42","entry":"get_transfrom_matrix","repo":"zhangyp15/MonoFlex","repo_kind":"official","path":"model/heatmap_coder.py","file_url":"https://github.com/zhangyp15/MonoFlex/blob/HEAD/model/heatmap_coder.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"194052ec40659a42"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}