{"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/multi-view-transformer-for-3d-visual","title":"Multi-View Transformer for 3D Visual Grounding","arxiv_id":"2204.02174","date":"2022-04-05","proceeding":"CVPR 2022 1","authors":["Shijia Huang","Yilun Chen","Jiaya Jia","LiWei Wang"],"abstract":"The 3D visual grounding task aims to ground a natural language description to the targeted object in a 3D scene, which is usually represented in 3D point clouds. Previous works studied visual grounding under specific views. The vision-language correspondence learned by this way can easily fail once the view changes. In this paper, we propose a Multi-View Transformer (MVT) for 3D visual grounding. We project the 3D scene to a multi-view space, in which the position information of the 3D scene under different views are modeled simultaneously and aggregated together. The multi-view space enables the network to learn a more robust multi-modal representation for 3D visual grounding and eliminates the dependence on specific views. Extensive experiments show that our approach significantly outperforms all state-of-the-art methods. Specifically, on Nr3D and Sr3D datasets, our method outperforms the best competitor by 11.2% and 7.1% and even surpasses recent work with extra 2D assistance by 5.9% and 6.6%. Our code is available at https://github.com/sega-hsj/MVT-3DVG.","url_abs":"https://arxiv.org/abs/2204.02174v1","url_pdf":"https://arxiv.org/pdf/2204.02174v1.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":"multi-view-transformer-for-3d-visual","repo_url":"https://github.com/sega-hsj/mvt-3dvg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-visual-grounding","task_name":"3D visual grounding"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.02174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02174"}},"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/sega-hsj/mvt-3dvg","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/sega-hsj/MVT-3DVG","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"8a2440331a528ad7","entry":"MLP","repo":"sega-hsj/MVT-3DVG","repo_kind":"official","path":"referit3d/models/referit3d_net.py","file_url":"https://github.com/sega-hsj/MVT-3DVG/blob/HEAD/referit3d/models/referit3d_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a2440331a528ad7"}},{"code_sha256_prefix":"aa2ec2ca752b21e7","entry":"get_siamese_features","repo":"sega-hsj/MVT-3DVG","repo_kind":"official","path":"referit3d/models/referit3d_net.py","file_url":"https://github.com/sega-hsj/MVT-3DVG/blob/HEAD/referit3d/models/referit3d_net.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":"aa2ec2ca752b21e7"}},{"code_sha256_prefix":"639c74e151322e56","entry":"optional_repeat","repo":"sega-hsj/MVT-3DVG","repo_kind":"official","path":"referit3d/models/referit3d_net.py","file_url":"https://github.com/sega-hsj/MVT-3DVG/blob/HEAD/referit3d/models/referit3d_net.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"639c74e151322e56"}},{"code_sha256_prefix":"50a3c270f973ab3c","entry":"ReferIt3DNet_transformer","repo":"sega-hsj/MVT-3DVG","repo_kind":"official","path":"referit3d/models/referit3d_net.py","file_url":"https://github.com/sega-hsj/MVT-3DVG/blob/HEAD/referit3d/models/referit3d_net.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":"50a3c270f973ab3c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}