{"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/hm-vit-hetero-modal-vehicle-to-vehicle","title":"HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer","arxiv_id":"2304.10628","date":"2023-04-20","proceeding":"ICCV 2023 1","authors":["Hao Xiang","Runsheng Xu","Jiaqi Ma"],"abstract":"Vehicle-to-Vehicle technologies have enabled autonomous vehicles to share information to see through occlusions, greatly enhancing perception performance. Nevertheless, existing works all focused on homogeneous traffic where vehicles are equipped with the same type of sensors, which significantly hampers the scale of collaboration and benefit of cross-modality interactions. In this paper, we investigate the multi-agent hetero-modal cooperative perception problem where agents may have distinct sensor modalities. We present HM-ViT, the first unified multi-agent hetero-modal cooperative perception framework that can collaboratively predict 3D objects for highly dynamic vehicle-to-vehicle (V2V) collaborations with varying numbers and types of agents. To effectively fuse features from multi-view images and LiDAR point clouds, we design a novel heterogeneous 3D graph transformer to jointly reason inter-agent and intra-agent interactions. The extensive experiments on the V2V perception dataset OPV2V demonstrate that the HM-ViT outperforms SOTA cooperative perception methods for V2V hetero-modal cooperative perception. We will release codes to facilitate future research.","url_abs":"https://arxiv.org/abs/2304.10628v1","url_pdf":"https://arxiv.org/pdf/2304.10628v1.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":"hm-vit-hetero-modal-vehicle-to-vehicle","repo_url":"https://github.com/xhwind/hm-vit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"}],"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":"graph-transformer","method_name":"Graph Transformer"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"lapeigen","method_name":"LapEigen"},{"method_slug":"laplacian-pe","method_name":"Laplacian PE"},{"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.10628","atlas_url":"https://app.syntology.ai/?focus=2304.10628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10628"}},"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/xhwind/hm-vit","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/XHwind/HM-ViT","reach":{"status":"ok"}}],"summary":{"ran":7,"ran_draft_wrong":4,"ran_honours":2,"ran_fixture":4,"unverified":4},"by_repo_kind":{"listed":{"samples":21,"ran":17,"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":21,"samples":[{"code_sha256_prefix":"798efccf36c7fcad","entry":"BaseSimpleHetero","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"798efccf36c7fcad"}},{"code_sha256_prefix":"3092961e509a12fa","entry":"HeteroAttention","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3092961e509a12fa"}},{"code_sha256_prefix":"ea77ad7518630d6c","entry":"HeteroFeedForward","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea77ad7518630d6c"}},{"code_sha256_prefix":"19f15a767ccb2fd1","entry":"HeteroLayerNorm","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"19f15a767ccb2fd1"}},{"code_sha256_prefix":"615d1b7ab30a3bed","entry":"HeteroPreNormResidual","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"615d1b7ab30a3bed"}},{"code_sha256_prefix":"7a14fc9972665140","entry":"RadixSoftmax","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a14fc9972665140"}},{"code_sha256_prefix":"0c71907cc87fd9b6","entry":"SplitAttn","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c71907cc87fd9b6"}},{"code_sha256_prefix":"f0f6c4d1d2c6420a","entry":"_torch_inverse_cast","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f0f6c4d1d2c6420a"}},{"code_sha256_prefix":"92584c2b3d356da1","entry":"combine_roi_and_cav_mask","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"92584c2b3d356da1"}},{"code_sha256_prefix":"8619a594ef3e41e9","entry":"convert_affinematrix_to_homography","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8619a594ef3e41e9"}},{"code_sha256_prefix":"2ddac2e2ccb49f1e","entry":"eye_like","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2ddac2e2ccb49f1e"}},{"code_sha256_prefix":"dcb869a37c5768e2","entry":"get_discretized_transformation_matrix","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcb869a37c5768e2"}},{"code_sha256_prefix":"9fa2fce5b7b0a7e7","entry":"get_rotation_matrix2d","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fa2fce5b7b0a7e7"}},{"code_sha256_prefix":"759f5a362c6e80f5","entry":"get_transformation_matrix","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"759f5a362c6e80f5"}},{"code_sha256_prefix":"9ddd573c88847902","entry":"normal_transform_pixel","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ddd573c88847902"}},{"code_sha256_prefix":"363cd89201e43095","entry":"normalize_homography","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"363cd89201e43095"}},{"code_sha256_prefix":"f18ebbe77a6b9723","entry":"warp_affine","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f18ebbe77a6b9723"}},{"code_sha256_prefix":"397df50741b19cab","entry":"HeteroFusionBlock","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"397df50741b19cab"}},{"code_sha256_prefix":"4159d82521f2938d","entry":"SpatialTransformation","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4159d82521f2938d"}},{"code_sha256_prefix":"a7e516a37cf8eaad","entry":"get_roi_and_cav_mask","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a7e516a37cf8eaad"}},{"code_sha256_prefix":"8ba77df1ce40565f","entry":"get_rotated_roi","repo":"XHwind/HM-ViT","repo_kind":"listed","path":"opencood/models/sub_modules/hetero_fusion.py","file_url":"https://github.com/XHwind/HM-ViT/blob/HEAD/opencood/models/sub_modules/hetero_fusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ba77df1ce40565f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}