ObjectMatch: Robust Registration using Canonical Object Correspondences
Can Gümeli, Angela Dai, Matthias Nießner
2023Year
6Top-tier citations
Abstract
Figure 1 . Modern camera pose estimation relies on feature matching between overlapping frames -in this work, we present ObjectMatch to find correspondences between frames with little or no overlap by predicting semantic mappings through canonical object correspondences. The images above share no direct overlap, yet our method establishes indirect correspondences, thus enabling a successful registration.
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 e85ae14e-e0ad-4a98-bd50-5a4f4be60bfdCited by top-tier papers6
- ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept VectorsLiming Kuang, Yordanka Velikova, Mahdi Saleh, Jan-Nico Zaech et al.CVPR 2026 · 5 citations
- X-SLAM: Scalable Dense SLAM for Task-aware Optimization using CSFDZhexi Peng, Yin Yang, Tianjia Shao, Chenfanfu Jiang et al.SIGGRAPH 2024 · 3 citations
- CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map GenerationDexin Zuo, Ang Li, Wei Wang, Wenxian Yu et al.AAAI 2026
- Any6D: Model-free 6D Pose Estimation of Novel ObjectsTaeyeop Lee, Bowen Wen, Minjun Kang, Gyuree Kang et al.CVPR 2025
- One2Any: One-Reference 6D Pose Estimation for Any ObjectMengya Liu, Siyuan Li, Ajad Chhatkuli, Prune Truong et al.CVPR 2025
Builds on14
- iMAP: Implicit Mapping and Positioning in Real-TimeEdgar Sucar, Shikun Liu, Joseph Ortiz, Andrew J. DavisonICCV 2021 · 834 citations
- Fully Convolutional Geometric FeaturesChristopher B. Choy, Jaesik Park, Vladlen KoltunICCV 2019 · 807 citations
- NICE-SLAM: Neural Implicit Scalable Encoding for SLAMZihan Zhu, Songyou Peng, Viktor Larsson, Weiwei Xu et al.CVPR 2022 · 720 citations
- Geometric Transformer for Fast and Robust Point Cloud RegistrationZheng Qin, Hao Yu, Changjian Wang, Yulan Guo et al.CVPR 2022 · 436 citations
- End-to-End CAD Model Retrieval and 9DoF Alignment in 3D ScansArmen Avetisyan, Angela Dai, Matthias NießnerICCV 2019 · 88 citations
Related papers
- Jamais Vu: Exposing the Generalization Gap in Supervised Semantic CorrespondenceOctave Mariotti, Zhipeng Du, Yash Bhalgat, Oisin Mac Aodha et al.NeurIPS 2025 · 8 citations
- Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D SequencesNorman Müller, Yu-Shiang Wong, Niloy J. Mitra, Angela Dai et al.CVPR 2021
- Articulation-Aware Canonical Surface MappingNilesh Kulkarni, Abhinav Gupta, David F. Fouhey, Shubham TulsianiCVPR 2020
- Matching 2D Images in 3D: Metric Relative Pose from Metric CorrespondencesAxel Barroso-Laguna, Sowmya Munukutla, Victor Adrian Prisacariu, Eric BrachmannCVPR 2024
- Visual Correspondence HallucinationHugo Germain, Vincent Lepetit, Guillaume BourmaudICLR 2022 · 11 citations
