{"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/orthographic-feature-transform-for-monocular","title":"Orthographic Feature Transform for Monocular 3D Object Detection","arxiv_id":"1811.08188","date":"2018-11-20","proceeding":null,"authors":["Thomas Roddick","Alex Kendall","Roberto Cipolla"],"abstract":"3D object detection from monocular images has proven to be an enormously\nchallenging task, with the performance of leading systems not yet achieving\neven 10\\% of that of LiDAR-based counterparts. One explanation for this\nperformance gap is that existing systems are entirely at the mercy of the\nperspective image-based representation, in which the appearance and scale of\nobjects varies drastically with depth and meaningful distances are difficult to\ninfer. In this work we argue that the ability to reason about the world in 3D\nis an essential element of the 3D object detection task. To this end, we\nintroduce the orthographic feature transform, which enables us to escape the\nimage domain by mapping image-based features into an orthographic 3D space.\nThis allows us to reason holistically about the spatial configuration of the\nscene in a domain where scale is consistent and distances between objects are\nmeaningful. We apply this transformation as part of an end-to-end deep learning\narchitecture and achieve state-of-the-art performance on the KITTI 3D object\nbenchmark.\\footnote{We will release full source code and pretrained models upon\nacceptance of this manuscript for publication.","url_abs":"http://arxiv.org/abs/1811.08188v1","url_pdf":"http://arxiv.org/pdf/1811.08188v1.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":"orthographic-feature-transform-for-monocular","repo_url":"https://github.com/tom-roddick/oft","is_official":0,"mentioned_in_paper":0,"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":"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.08188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08188"}},"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/tom-roddick/oft","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":12},"by_repo_kind":{"listed":{"samples":14,"ran":2,"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":"d9def42110729a85","entry":"conv1x1","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/model/resnet.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/model/resnet.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":"d9def42110729a85"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/model/resnet.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/model/resnet.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":"c4c53b042e331d71","entry":"draw_bbox2d","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/visualization/bbox.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/visualization/bbox.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":"c4c53b042e331d71"}},{"code_sha256_prefix":"4fd87f0f0ac889ed","entry":"hard_neg_mining_loss","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/model/loss.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/model/loss.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":"4fd87f0f0ac889ed"}},{"code_sha256_prefix":"0b86ddb1ed52bd06","entry":"huber_loss","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/model/loss.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/model/loss.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":"0b86ddb1ed52bd06"}},{"code_sha256_prefix":"9b8dad6c59d24b6a","entry":"integral_image","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/model/oft.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/model/oft.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":"9b8dad6c59d24b6a"}},{"code_sha256_prefix":"106667149eaee681","entry":"make_grid","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/utils.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/utils.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":"106667149eaee681"}},{"code_sha256_prefix":"80593b4e9f5c5518","entry":"masked_l1_loss","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/model/loss.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/model/loss.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":"80593b4e9f5c5518"}},{"code_sha256_prefix":"e326fc2e9a0e294f","entry":"perspective","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/utils.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/utils.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":"e326fc2e9a0e294f"}},{"code_sha256_prefix":"a35ec4d2d20ef74f","entry":"resnet18","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/model/resnet.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/model/resnet.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":"a35ec4d2d20ef74f"}},{"code_sha256_prefix":"bd6e2262574e30ca","entry":"rotate","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/utils.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/utils.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":"bd6e2262574e30ca"}},{"code_sha256_prefix":"83e909b403b17079","entry":"vis_score","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/visualization/encoded.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/visualization/encoded.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":"83e909b403b17079"}},{"code_sha256_prefix":"d38b6a865e78dc3c","entry":"vis_uncertainty","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/visualization/encoded.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/visualization/encoded.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":"d38b6a865e78dc3c"}},{"code_sha256_prefix":"ff1fa22d9f41d94e","entry":"visualize_objects","repo":"tom-roddick/oft","repo_kind":"listed","path":"oft/visualization/bbox.py","file_url":"https://github.com/tom-roddick/oft/blob/HEAD/oft/visualization/bbox.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":"ff1fa22d9f41d94e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}