{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:24:06Z","timestamp":1766132646843,"version":"3.48.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246449","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"15375-15382","source":"Crossref","is-referenced-by-count":0,"title":["RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base"],"prefix":"10.1109","author":[{"given":"Kuanning","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqian","family":"Fu","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University \"St. Kliment Ohridski\",Bulgaria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longfei","family":"Liang","sequence":"additional","affiliation":[{"name":"NeuhHelium Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes","year":"2017","author":"Xiang","key":"ref1"},{"volume-title":"Mrc-net: 6-dof pose estimation with multiscale residual correlation","year":"2024","author":"Li","key":"ref2"},{"key":"ref3","first-page":"7677","article-title":"Cdpn: Coordinates-based disentangled pose network for real-time rgb-based 6-dof object pose estimation","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Li"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20077-9_22","article-title":"Dcl-net: Deep correspondence learning network for 6d pose estimation","volume-title":"European Conference on Computer Vision","author":"Li"},{"key":"ref5","first-page":"3404","article-title":"Center-based decoupled point cloud registration for 6d object pose estimation","volume-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Jiang"},{"volume-title":"Dinov2: Learning robust visual features without supervision","year":"2023","author":"Oquab","key":"ref6"},{"key":"ref7","first-page":"2938","article-title":"Posenet: A convolutional network for real-time 6-dof camera relocalization","volume-title":"2015 IEEE International Conference on Computer Vision (ICCV)","author":"Kendall"},{"key":"ref8","first-page":"16606","article-title":"Gdr-net: Geometryguided direct regression network for monocular 6d object pose estimation","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang"},{"key":"ref9","first-page":"4556","article-title":"Pvnet: Pixel-wise voting network for 6dof pose estimation","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Peng"},{"key":"ref10","first-page":"7667","article-title":"Pix2pose: Pixel-wise coordinate regression of objects for 6d pose estimation","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Park"},{"key":"ref11","first-page":"6739","article-title":"Surfemb: Dense and continuous correspondence distributions for object pose estimation with learnt surface embeddings","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Haugaard"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref13","first-page":"7417","article-title":"Dpodv2: Dense correspondence-based 6 dof pose estimation","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"44","author":"Shugurov","year":"2021"},{"key":"ref14","first-page":"103950","article-title":"Prior-information-guided corresponding point regression network for 6d pose estimation","volume-title":"Comput. Graph","volume":"121","author":"Gan","year":"2024"},{"volume-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","year":"2020","author":"Lewis","key":"ref15"},{"article-title":"Retrieval augmented generation and understanding in vision: A survey and new outlook","year":"2025","author":"Zheng","key":"ref16"},{"key":"ref17","first-page":"19265","article-title":"Raclip: Retrieval augmented contrastive language-image pre-training","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xie"},{"article-title":"Realrag: Retrieval-augmented realistic image generation via self-reflective contrastive learning","year":"2025","author":"Lyu","key":"ref18"},{"article-title":"Domain-rag: Retrieval-guided compositional image generation for cross-domain few-shot object detection","year":"2025","author":"Li","key":"ref19"},{"article-title":"Beyond text: Optimizing rag with multimodal inputs for industrial applications","year":"2024","author":"Riedler","key":"ref20"},{"volume-title":"Implicit neural representations with periodic activation functions","year":"2020","author":"Sitzmann","key":"ref21"},{"volume-title":"D3fields: Dynamic 3d descriptor fields for zero-shot generalizable robotic manipulation","year":"2023","author":"Wang","key":"ref22"},{"article-title":"Freeze: Training-free zero-shot 6d pose estimation with geometric and vision foundation models","year":"2023","author":"Caraffa","key":"ref23"},{"volume-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","year":"2023","author":"Huang","key":"ref24"},{"key":"ref25","first-page":"77","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Qi"},{"key":"ref26","first-page":"5987","article-title":"Aggregated residual transformations for deep neural networks","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xie"},{"volume-title":"U-net: Convolutional networks for biomedical image segmentation","year":"2015","author":"Ronneberger","key":"ref27"},{"volume-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0152-6"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-10605-2_35","article-title":"Learning 6d object pose estimation using 3d object coordinates","volume-title":"European Conference on Computer Vision","author":"Brachmann"},{"key":"ref31","first-page":"3583","article-title":"Recovering 6d object pose and predicting next-best-view in the crowd","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Doumanoglou"},{"key":"ref32","first-page":"2767","article-title":"Homebreweddb: Rgb-d dataset for 6d pose estimation of 3d objects","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW)","author":"Kaskman"},{"volume-title":"Bop: Benchmark for 6d object pose estimation","year":"2018","author":"Hodan","key":"ref33"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW63382.2024.00570","article-title":"Bop challenge 2023 on detection, segmentation and pose estimation of seen and unseen rigid objects","author":"Hodan","year":"2024"},{"key":"ref35","first-page":"2126","article-title":"Cnos: A strong baseline for cad-based novel object segmentation","volume-title":"2023 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","author":"Nguyen"},{"volume-title":"Bop challenge 2020 on 6d object localization","year":"2020","author":"Hodan","key":"ref36"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20080-9_34","article-title":"Neural correspondence field for object pose estimation","volume-title":"European Conference on Computer Vision","author":"Huang"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58520-4_34","article-title":"Cosypose: Consistent multi-view multi-object 6d pose estimation","volume-title":"European Conference on Computer Vision","author":"Labb\u2019e"},{"key":"ref39","first-page":"12376","article-title":"Sopose: Exploiting self-occlusion for direct 6d pose estimation","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Di"},{"key":"ref40","first-page":"5735","article-title":"Crt-6d: Fast 6d object pose estimation with cascaded refinement transformers","volume-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Castro"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20086-1_6","article-title":"Perspective flow aggregation for data-limited 6d object pose estimation","volume-title":"European Conference on Computer Vision","author":"Hu"},{"key":"ref42","first-page":"1616","article-title":"Yolo-6d-pose: Enhancing yolo for single-stage monocular multi-object 6d pose estimation","volume-title":"2024 International Conference on 3D Vision (3DV)","author":"Maji"},{"key":"ref43","first-page":"145","article-title":"Efficient variants of the icp algorithm","volume-title":"Proceedings Third International Conference on 3-D Digital Imaging and Modeling","author":"Rusinkiewicz"},{"key":"ref44","first-page":"1198","article-title":"Corri2p: Deep image-to-point cloud registration via dense correspondence","volume-title":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"33","author":"Ren","year":"2022"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246449.pdf?arnumber=11246449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:19:56Z","timestamp":1766132396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246449","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}