3D-Object Perception Transformer (3PT)
Agastya Kalra, Tim Salzmann, Guy Stoppi, Dmitrii Marin, Rishav Agarwal, Vage Taamazyan, Martin Bokeloh, Stefan Hinterstoisser, Anton Boykov, Alberto Dall'Olio, Pravin Dangol, Kartik Venkataraman, Huaijin Chen
Abstract
Detection (Rel. AP) Pose (AP-mm on BOP-Ind.) 6D Pose Figure 1. 3PT achieves state-of-the-art zero-shot 3D object perception, including detection, segmentation, and 6DoF pose estimation. Unlike previous methods, 3PT successfully reconstructs poses in complex industrial scenes, such as the bracket houseof-cards structure shown above.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext d7eeb1d7-96d2-4a38-8b0f-0601e07a1c8cBuilds on19
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- Vision Transformers for Dense PredictionRené Ranftl, Alexey Bochkovskiy, Vladlen KoltunICCV 2021 · 2,647 citations
- Scaling Open-Vocabulary Object DetectionMatthias Minderer, Alexey A. Gritsenko, Neil HoulsbyNeurIPS 2023 · 482 citations
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel ObjectsBowen Wen, Wei Yang, Jan Kautz, Stan BirchfieldCVPR 2024 · 215 citations
Related papers
- OSOP: A Multi-Stage One Shot Object Pose Estimation FrameworkIvan Shugurov, Fu Li, Benjamin Busam, Slobodan IlicCVPR 2022 · 86 citations
- SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose EstimationJiehong Lin, Lihua Liu, Dekun Lu, Kui JiaCVPR 2024
- Universal Features Guided Zero-Shot Category-Level Object Pose EstimationWentian Qu, Chenyu Meng, Heng Li, Jian Cheng et al.AAAI 2025
- GigaPose: Fast and Robust Novel Object Pose Estimation via One CorrespondenceVan Nguyen Nguyen, Thibault Groueix, Mathieu Salzmann, Vincent LepetitCVPR 2024 · 67 citations
- L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud StreamJingtao Sun, Yaonan Wang, Mingtao Feng, Yulan Guo et al.CVPR 2024 · 1 citation
