{"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/rethinking-3d-dense-caption-and-visual","title":"Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization","arxiv_id":"2404.11064","date":"2024-04-17","proceeding":null,"authors":["Yongdong Luo","Haojia Lin","Xiawu Zheng","Yigeng Jiang","Fei Chao","Jie Hu","Guannan Jiang","Songan Zhang","Rongrong Ji"],"abstract":"3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships. Therefore, existing approaches adopt the two-stage \"detect-then-describe/discriminate\" pipeline, which relies heavily on the performance of the detector, resulting in suboptimal performance. Inspired by DETR, we propose a unified framework, 3DGCTR, to jointly solve these two distinct but closely related tasks in an end-to-end fashion. The key idea is to reconsider the prompt-based localization ability of the 3DVG model. In this way, the 3DVG model with a well-designed prompt as input can assist the 3DDC task by extracting localization information from the prompt. In terms of implementation, we integrate a Lightweight Caption Head into the existing 3DVG network with a Caption Text Prompt as a connection, effectively harnessing the existing 3DVG model's inherent localization capacity, thereby boosting 3DDC capability. This integration facilitates simultaneous multi-task training on both tasks, mutually enhancing their performance. Extensive experimental results demonstrate the effectiveness of this approach. Specifically, on the ScanRefer dataset, 3DGCTR surpasses the state-of-the-art 3DDC method by 4.3% in CIDEr@0.5IoU in MLE training and improves upon the SOTA 3DVG method by 3.16% in Acc@0.25IoU. The codes are at https://github.com/Leon1207/3DGCTR.","url_abs":"https://arxiv.org/abs/2404.11064v3","url_pdf":"https://arxiv.org/pdf/2404.11064v3.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":"rethinking-3d-dense-caption-and-visual","repo_url":"https://github.com/leon1207/3dgctr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-dense-captioning","task_name":"3D dense captioning"},{"task_slug":"3d-visual-grounding","task_name":"3D visual grounding"},{"task_slug":"dense-captioning","task_name":"Dense Captioning"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}