{"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/3d-vision-and-language-pretraining-with-large","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data","arxiv_id":"2407.06084","date":"2024-07-08","proceeding":null,"authors":["Dejie Yang","Zhu Xu","Wentao Mo","Qingchao Chen","Siyuan Huang","Yang Liu"],"abstract":"3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited scene-level diversity and insufficient fine-grained annotations (only 1.2K scenes and 280K textual annotations in ScanScribe), primarily due to the labor-intensive of collecting and annotating 3D scenes. To overcome these obstacles, we construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, and room levels, which has the advantages of diverse scene data, rich textual descriptions, multi-grained 3D-text associations, and low collection cost. Utilizing the rich annotations in SynVL3D, we pre-train a simple and unified Transformer for aligning 3D and language with multi-grained pretraining tasks. Moreover, we propose a synthetic-to-real domain adaptation in downstream task fine-tuning process to address the domain shift. Through extensive experiments, we verify the effectiveness of our model design by achieving state-of-the-art performance on downstream tasks including visual grounding, dense captioning, and question answering.","url_abs":"https://arxiv.org/abs/2407.06084v1","url_pdf":"https://arxiv.org/pdf/2407.06084v1.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":"3d-vision-and-language-pretraining-with-large","repo_url":"https://github.com/idejie/3DSyn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dense-captioning","task_name":"Dense Captioning"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"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":{"syntology_url":"https://syntology.ai/paper/2407.06084","atlas_url":"https://app.syntology.ai/?focus=2407.06084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06084"}},"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":"deterministic:regex_extraction","url":"https://github.com/idejie/3DSyn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran":9},"by_repo_kind":{"official":{"samples":10,"ran":10,"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":"aab935d4b7b55c2c","entry":"in_hull","repo":"idejie/3DSyn","repo_kind":"official","path":"scannet/model_util_scannet.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/scannet/model_util_scannet.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aab935d4b7b55c2c"}},{"code_sha256_prefix":"be1fe3da19cb1fd1","entry":"compute_normal","repo":"idejie/3DSyn","repo_kind":"official","path":"scannet/scannet_utils.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/scannet/scannet_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be1fe3da19cb1fd1"}},{"code_sha256_prefix":"50bdbf961c28b4b2","entry":"extract_pc_in_box3d","repo":"idejie/3DSyn","repo_kind":"official","path":"scannet/model_util_scannet.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/scannet/model_util_scannet.py","link_basis":"first_harvest_node","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":"50bdbf961c28b4b2"}},{"code_sha256_prefix":"e718b6389b360792","entry":"normalize_v3","repo":"idejie/3DSyn","repo_kind":"official","path":"scannet/scannet_utils.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/scannet/scannet_utils.py","link_basis":"first_harvest_node","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":"e718b6389b360792"}},{"code_sha256_prefix":"f68277b7b645f232","entry":"random_caption_word","repo":"idejie/3DSyn","repo_kind":"official","path":"dataset/data_converter.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/dataset/data_converter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f68277b7b645f232"}},{"code_sha256_prefix":"1e399fcc55e7f292","entry":"random_point_cloud","repo":"idejie/3DSyn","repo_kind":"official","path":"dataset/data_converter.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/dataset/data_converter.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e399fcc55e7f292"}},{"code_sha256_prefix":"7f50e9ea5a5a0a0a","entry":"read_aggregation","repo":"idejie/3DSyn","repo_kind":"official","path":"scannet/load_scannet_data.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/scannet/load_scannet_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f50e9ea5a5a0a0a"}},{"code_sha256_prefix":"f124539052ae9169","entry":"read_segmentation","repo":"idejie/3DSyn","repo_kind":"official","path":"scannet/load_scannet_data.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/scannet/load_scannet_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f124539052ae9169"}},{"code_sha256_prefix":"2857904cc41e5290","entry":"represents_int","repo":"idejie/3DSyn","repo_kind":"official","path":"scannet/scannet_utils.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/scannet/scannet_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2857904cc41e5290"}},{"code_sha256_prefix":"7457a44fbe4c2d1d","entry":"rotate_aligned_boxes","repo":"idejie/3DSyn","repo_kind":"official","path":"scannet/model_util_scannet.py","file_url":"https://github.com/idejie/3DSyn/blob/HEAD/scannet/model_util_scannet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7457a44fbe4c2d1d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}