{"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/vlm-grounder-a-vlm-agent-for-zero-shot-3d","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","arxiv_id":"2410.13860","date":"2024-10-17","proceeding":null,"authors":["Runsen Xu","Zhiwei Huang","Tai Wang","Yilun Chen","Jiangmiao Pang","Dahua Lin"],"abstract":"3D visual grounding is crucial for robots, requiring integration of natural language and 3D scene understanding. Traditional methods depending on supervised learning with 3D point clouds are limited by scarce datasets. Recently zero-shot methods leveraging LLMs have been proposed to address the data issue. While effective, these methods only use object-centric information, limiting their ability to handle complex queries. In this work, we present VLM-Grounder, a novel framework using vision-language models (VLMs) for zero-shot 3D visual grounding based solely on 2D images. VLM-Grounder dynamically stitches image sequences, employs a grounding and feedback scheme to find the target object, and uses a multi-view ensemble projection to accurately estimate 3D bounding boxes. Experiments on ScanRefer and Nr3D datasets show VLM-Grounder outperforms previous zero-shot methods, achieving 51.6% Acc@0.25 on ScanRefer and 48.0% Acc on Nr3D, without relying on 3D geometry or object priors. Codes are available at https://github.com/OpenRobotLab/VLM-Grounder .","url_abs":"https://arxiv.org/abs/2410.13860v1","url_pdf":"https://arxiv.org/pdf/2410.13860v1.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":"vlm-grounder-a-vlm-agent-for-zero-shot-3d","repo_url":"https://github.com/openrobotlab/vlm-grounder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":"3d-visual-grounding","task_name":"3D visual grounding"},{"task_slug":"object","task_name":"Object"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.13860","atlas_url":"https://app.syntology.ai/?focus=2410.13860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13860"}},"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/openrobotlab/vlm-grounder","reach":{"status":"ok"}}],"summary":{"ran":10,"unverified":1},"by_repo_kind":{"official":{"samples":11,"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":11,"samples":[{"code_sha256_prefix":"d35a5313e1b5a9fc","entry":"calculate_image_sharpness","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/ops.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/ops.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":"d35a5313e1b5a9fc"}},{"code_sha256_prefix":"9b98bf2093e792ed","entry":"convert_to_corners","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/ops.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/ops.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":"9b98bf2093e792ed"}},{"code_sha256_prefix":"70a2bd375125d650","entry":"encode_PIL_image_to_base64","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/grid_image_generator.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/grid_image_generator.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":"70a2bd375125d650"}},{"code_sha256_prefix":"e97541e4a6e9ea11","entry":"filter_images_laplacian","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/ops.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/ops.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":"e97541e4a6e9ea11"}},{"code_sha256_prefix":"3b489f8be2d3b79d","entry":"get_csv_row","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/grounder/visual_grouder.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/grounder/visual_grouder.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":"3b489f8be2d3b79d"}},{"code_sha256_prefix":"e6b413e956fb1640","entry":"get_scene_ids_from_csv","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/csv_utils.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/csv_utils.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":"e6b413e956fb1640"}},{"code_sha256_prefix":"ea5a2af68864cf1d","entry":"resize_image","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/grid_image_generator.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/grid_image_generator.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":"ea5a2af68864cf1d"}},{"code_sha256_prefix":"c8cf6cb9cddae6c9","entry":"resize_image_to_GPT_size","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/grid_image_generator.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/grid_image_generator.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":"c8cf6cb9cddae6c9"}},{"code_sha256_prefix":"e422c96b99ba09d6","entry":"retry_with_exponential_backoff","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/my_openai.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/my_openai.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":"e422c96b99ba09d6"}},{"code_sha256_prefix":"faf7e416de9cc8d4","entry":"retry_with_exponential_backoff","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/online_detector.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/online_detector.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":"faf7e416de9cc8d4"}},{"code_sha256_prefix":"ebf182c27ea4ae72","entry":"filter_image_url","repo":"openrobotlab/vlm-grounder","repo_kind":"official","path":"vlm_grounder/utils/my_openai.py","file_url":"https://github.com/openrobotlab/vlm-grounder/blob/HEAD/vlm_grounder/utils/my_openai.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":"ebf182c27ea4ae72"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}