{"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/an-end-to-end-transformer-model-for-3d-object","title":"An End-to-End Transformer Model for 3D Object Detection","arxiv_id":"2109.08141","date":"2021-09-16","proceeding":"ICCV 2021 10","authors":["Ishan Misra","Rohit Girdhar","Armand Joulin"],"abstract":"We propose 3DETR, an end-to-end Transformer based object detection model for 3D point clouds. Compared to existing detection methods that employ a number of 3D-specific inductive biases, 3DETR requires minimal modifications to the vanilla Transformer block. Specifically, we find that a standard Transformer with non-parametric queries and Fourier positional embeddings is competitive with specialized architectures that employ libraries of 3D-specific operators with hand-tuned hyperparameters. Nevertheless, 3DETR is conceptually simple and easy to implement, enabling further improvements by incorporating 3D domain knowledge. Through extensive experiments, we show 3DETR outperforms the well-established and highly optimized VoteNet baselines on the challenging ScanNetV2 dataset by 9.5%. Furthermore, we show 3DETR is applicable to 3D tasks beyond detection, and can serve as a building block for future research.","url_abs":"https://arxiv.org/abs/2109.08141v1","url_pdf":"https://arxiv.org/pdf/2109.08141v1.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":"an-end-to-end-transformer-model-for-3d-object","repo_url":"https://github.com/facebookresearch/3detr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"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-on-sun-rgbd-val","task":"3D Object Detection","dataset":"SUN-RGBD val","model":"3DETR-m","rank_in_archive_order":23,"of":32,"metrics":{"mAP@0.25":"59.1","mAP@0.5":"32.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-scannetv2","task":"3D Object Detection","dataset":"ScanNetV2","model":"3DETR-m","rank_in_archive_order":24,"of":33,"metrics":{"mAP@0.25":"65.0","mAP@0.5":"47.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.08141","atlas_url":"https://app.syntology.ai/?focus=2109.08141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08141"}},"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/facebookresearch/3detr","reach":null}],"summary":{"ran":4,"ran_honours":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":6,"ran":5,"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":1,"samples":[{"code_sha256_prefix":"d5a77f2ff6399442","entry":"BatchNormDim1Swap","repo":"facebookresearch/3detr","repo_kind":"listed","path":"models/model_3detr.py","file_url":"https://github.com/facebookresearch/3detr/blob/HEAD/models/model_3detr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d5a77f2ff6399442"}},{"code_sha256_prefix":"a91c6967a4ff8553","entry":"BoxProcessor","repo":"facebookresearch/3detr","repo_kind":"listed","path":"models/model_3detr.py","file_url":"https://github.com/facebookresearch/3detr/blob/HEAD/models/model_3detr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a91c6967a4ff8553"}},{"code_sha256_prefix":"571333c23ae0f3ed","entry":"GenericMLP","repo":"facebookresearch/3detr","repo_kind":"listed","path":"models/model_3detr.py","file_url":"https://github.com/facebookresearch/3detr/blob/HEAD/models/model_3detr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"571333c23ae0f3ed"}},{"code_sha256_prefix":"354fe5ecc3240909","entry":"PositionEmbeddingCoordsSine","repo":"facebookresearch/3detr","repo_kind":"listed","path":"models/model_3detr.py","file_url":"https://github.com/facebookresearch/3detr/blob/HEAD/models/model_3detr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"354fe5ecc3240909"}},{"code_sha256_prefix":"c2546a46c7f63930","entry":"scale_points","repo":"facebookresearch/3detr","repo_kind":"listed","path":"models/model_3detr.py","file_url":"https://github.com/facebookresearch/3detr/blob/HEAD/models/model_3detr.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2546a46c7f63930"}},{"code_sha256_prefix":"818099bdffc93897","entry":"shift_scale_points","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"818099bdffc93897"}},{"code_sha256_prefix":"5ba9ad4c9902d06c","entry":"Model3DETR","repo":"facebookresearch/3detr","repo_kind":"listed","path":"models/model_3detr.py","file_url":"https://github.com/facebookresearch/3detr/blob/HEAD/models/model_3detr.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":"5ba9ad4c9902d06c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}