{"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/monodtr-monocular-3d-object-detection-with","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","arxiv_id":"2203.10981","date":"2022-03-21","proceeding":"CVPR 2022 1","authors":["Kuan-Chih Huang","Tsung-Han Wu","Hung-Ting Su","Winston H. Hsu"],"abstract":"Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to assist 3D detection, but suffer from the additional computational burden and achieve limited performance caused by inaccurate depth priors. To alleviate this, we propose MonoDTR, a novel end-to-end depth-aware transformer network for monocular 3D object detection. It mainly consists of two components: (1) the Depth-Aware Feature Enhancement (DFE) module that implicitly learns depth-aware features with auxiliary supervision without requiring extra computation, and (2) the Depth-Aware Transformer (DTR) module that globally integrates context- and depth-aware features. Moreover, different from conventional pixel-wise positional encodings, we introduce a novel depth positional encoding (DPE) to inject depth positional hints into transformers. Our proposed depth-aware modules can be easily plugged into existing image-only monocular 3D object detectors to improve the performance. Extensive experiments on the KITTI dataset demonstrate that our approach outperforms previous state-of-the-art monocular-based methods and achieves real-time detection. Code is available at https://github.com/kuanchihhuang/MonoDTR","url_abs":"https://arxiv.org/abs/2203.10981v2","url_pdf":"https://arxiv.org/pdf/2203.10981v2.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":"monodtr-monocular-3d-object-detection-with","repo_url":"https://github.com/kuanchihhuang/monodtr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"3d-object-detection-from-monocular-images","task_name":"3D Object Detection From Monocular Images"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"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":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-from-monocular-images-on-7","task":"3D Object Detection From Monocular Images","dataset":"KITTI-360","model":"MonoDTR","rank_in_archive_order":5,"of":11,"metrics":{"AP25":"39.76","AP50":"3.02"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.10981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10981"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/kuanchihhuang/monodtr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":8,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"kuanchihhuang/monodtr","repo_kind":"official","path":"visualDet3D/networks/backbones/dla.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/backbones/dla.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":"fac5364e2f53c6db"}},{"code_sha256_prefix":"0d5505bd782b4a89","entry":"elu_feature_map","repo":"kuanchihhuang/monodtr","repo_kind":"official","path":"visualDet3D/networks/detectors/dtr.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/detectors/dtr.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d5505bd782b4a89"}},{"code_sha256_prefix":"3c9867a84d7c18d9","entry":"get_model_url","repo":"kuanchihhuang/monodtr","repo_kind":"official","path":"visualDet3D/networks/backbones/dla.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/backbones/dla.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c9867a84d7c18d9"}},{"code_sha256_prefix":"2a214da3b52ccc74","entry":"anchors_for_shape","repo":"kuanchihhuang/monodtr","repo_kind":"official","path":"visualDet3D/networks/heads/anchors.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/heads/anchors.py","link_basis":"harvester_set","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":"2a214da3b52ccc74"}},{"code_sha256_prefix":"87726458df330951","entry":"bin_depths","repo":"kuanchihhuang/monodtr","repo_kind":"official","path":"visualDet3D/networks/heads/depth_losses.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/heads/depth_losses.py","link_basis":"harvester_set","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":"87726458df330951"}},{"code_sha256_prefix":"0e14588c12c9c1b4","entry":"compute_shape","repo":"kuanchihhuang/monodtr","repo_kind":"official","path":"visualDet3D/networks/heads/anchors.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/heads/anchors.py","link_basis":"harvester_set","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":"0e14588c12c9c1b4"}},{"code_sha256_prefix":"1e380a5690a619ef","entry":"dla34","repo":"kuanchihhuang/monodtr","repo_kind":"official","path":"visualDet3D/networks/backbones/dla.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/backbones/dla.py","link_basis":"harvester_set","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":"1e380a5690a619ef"}},{"code_sha256_prefix":"1279986e0f62b111","entry":"generate_anchors","repo":"kuanchihhuang/monodtr","repo_kind":"official","path":"visualDet3D/networks/heads/anchors.py","file_url":"https://github.com/kuanchihhuang/monodtr/blob/HEAD/visualDet3D/networks/heads/anchors.py","link_basis":"harvester_set","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":"1279986e0f62b111"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}