CVPR 2026 Open Access Repository

Unified Robotic Vision with Cross-Modal Sensing and Alignment

GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth: Krishna Jaganathan,

Patricio Vela; [pdf] [arXiv]
[bibtex]
@InProceedings{Jaganathan_2026_CVPR, author = {Jaganathan, Krishna and Vela, Patricio}, title = {GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8268-8278} }
MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL: Mahmoud SalahEldin Kasem,

Mohamed Mahmoud,

Mostafa Farouk Senussi,

Mahmoud Abdalla,

Abdelrahman Abdallah,

Hyun-Soo Kang; [pdf] [arXiv]
[bibtex]
@InProceedings{Kasem_2026_CVPR, author = {Kasem, Mahmoud SalahEldin and Mahmoud, Mohamed and Senussi, Mostafa Farouk and Abdalla, Mahmoud and Abdallah, Abdelrahman and Kang, Hyun-Soo}, title = {MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8279-8288} }
Adverse-to-the-eXtreme Panoptic Segmentation: URVIS 2026 Study and Benchmark: Yiting Wang,

Nolwenn Peyratout,

Tim Broedermann,

Jiahui Wang,

Yusi Cao,

Michele Cazzola,

Elie Tarassov,

Takuya Kobayashi,

Abderrahim Kasmi,

Guillaume Allibert,

Cédric Demonceaux,

Valentina Donzella,

Kurt Debattista,

Radu Timofte,

Zongwei Wu,

Christos Sakaridis; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2026_CVPR, author = {Wang, Yiting and Peyratout, Nolwenn and Broedermann, Tim and Wang, Jiahui and Cao, Yusi and Cazzola, Michele and Tarassov, Elie and Kobayashi, Takuya and Kasmi, Abderrahim and Allibert, Guillaume and Demonceaux, C\'edric and Donzella, Valentina and Debattista, Kurt and Timofte, Radu and Wu, Zongwei and Sakaridis, Christos}, title = {Adverse-to-the-eXtreme Panoptic Segmentation: URVIS 2026 Study and Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8346-8354} }
Toward Efficient Visual Gyroscopes: Spherical Moments, Harmonics Filtering, and Masking Techniques for Spherical Camera Applications: Yao Du,

Carlos Mateo,

Mirjana Maras,

Tsun-Hsuan Wang,

Marc Blanchon,

Alexander Amini,

Daniela Rus,

Omar Tahri; [pdf] [arXiv]
[bibtex]
@InProceedings{Du_2026_CVPR, author = {Du, Yao and Mateo, Carlos and Maras, Mirjana and Wang, Tsun-Hsuan and Blanchon, Marc and Amini, Alexander and Rus, Daniela and Tahri, Omar}, title = {Toward Efficient Visual Gyroscopes: Spherical Moments, Harmonics Filtering, and Masking Techniques for Spherical Camera Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8248-8256} }
Object Tracking in the Real World: URVIS 2026 Study and Benchmark: Andong Lu,

Zhaodong Ding,

Chenglong Li,

Jin Tang,

Zongwei Wu,

Yuedong Tan,

Radu Timofte,

Xiantao Hu,

He Wang,

Zhangyong Tang,

Tianyang Xu,

Xiaojun Wu,

Ying Tai,

Jian Yang,

Yabin Zhu,

Chunhui Zhang,

Li Liu,

Hao Wen,

Xi Zhou,

Yanfeng Wang,

Shilei Wang,

Yipin Du,

Yongkang Cheng,

Pujian Lai,

Dong Gao,

Gong Cheng,

Jihuan Xi,

Yong Zhou,

Jinglin Zhou,

Xuefeng Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2026_CVPR, author = {Lu, Andong and Ding, Zhaodong and Li, Chenglong and Tang, Jin and Wu, Zongwei and Tan, Yuedong and Timofte, Radu and Hu, Xiantao and Wang, He and Tang, Zhangyong and Xu, Tianyang and Wu, Xiaojun and Tai, Ying and Yang, Jian and Zhu, Yabin and Zhang, Chunhui and Liu, Li and Wen, Hao and Zhou, Xi and Wang, Yanfeng and Wang, Shilei and Du, Yipin and Cheng, Yongkang and Lai, Pujian and Gao, Dong and Cheng, Gong and Xi, Jihuan and Zhou, Yong and Zhou, Jinglin and Zhu, Xuefeng}, title = {Object Tracking in the Real World: URVIS 2026 Study and Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8299-8307} }
GBG-SLAM: Key-frame Centered Monocular Gaussian SLAM with Scale Consistent Dense Geometry Boosting: Chuanmao Fan,

Chenxi Zhao,

Ye Duan; [pdf] [supp]
[bibtex]
@InProceedings{Fan_2026_CVPR, author = {Fan, Chuanmao and Zhao, Chenxi and Duan, Ye}, title = {GBG-SLAM: Key-frame Centered Monocular Gaussian SLAM with Scale Consistent Dense Geometry Boosting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8257-8267} }
Event-to-Frame Vehicle Re-identification for Heterogeneous Camera Networks: Dataset and Algorithm: Nitesh Menon,

Scott McCloskey; [pdf]
[bibtex]
@InProceedings{Menon_2026_CVPR, author = {Menon, Nitesh and McCloskey, Scott}, title = {Event-to-Frame Vehicle Re-identification for Heterogeneous Camera Networks: Dataset and Algorithm}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8318-8327} }
SIR: Structured Image Representations for Explainable Robot Learning: Paul Mattes,

Jan Schwab,

Jens Bosch,

Nils Blank,

Maximilian Xiling Li,

Minh-Trung Tang,

Moritz Haberland,

Rudolf Lioutikov; [pdf] [supp]
[bibtex]
@InProceedings{Mattes_2026_CVPR, author = {Mattes, Paul and Schwab, Jan and Bosch, Jens and Blank, Nils and Li, Maximilian Xiling and Tang, Minh-Trung and Haberland, Moritz and Lioutikov, Rudolf}, title = {SIR: Structured Image Representations for Explainable Robot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8308-8317} }
InfoCalib: Information-Theoretic Collapse Diagnosis and Dynamic Calibration for Robust Multimodal Frequency Fusion: Shenzhi Li,

Boao Qin,

Peng Wang,

Rangyu Deng; [pdf]
[bibtex]
@InProceedings{Li_2026_CVPR, author = {Li, Shenzhi and Qin, Boao and Wang, Peng and Deng, Rangyu}, title = {InfoCalib: Information-Theoretic Collapse Diagnosis and Dynamic Calibration for Robust Multimodal Frequency Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8289-8298} }
Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens: Ciem Cornelissen,

Sam Leroux,

Pieter Simoens; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cornelissen_2026_CVPR, author = {Cornelissen, Ciem and Leroux, Sam and Simoens, Pieter}, title = {Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8238-8247} }
Hear2See: Speech-Driven Visual Reasoning under Linguistic Variability: Joel Santos,

Zongwei Wu,

Radu Timofte; [pdf]
[bibtex]
@InProceedings{Santos_2026_CVPR, author = {Santos, Joel and Wu, Zongwei and Timofte, Radu}, title = {Hear2See: Speech-Driven Visual Reasoning under Linguistic Variability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8328-8337} }
DCTrack: Divide-and-Conquer for Modality-Missing RGBT Tracking: Shilei Wang,

Yipin Du,

Yongkang Cheng,

Pujian Lai,

Dong Gao,

Gong Cheng; [pdf]
[bibtex]
@InProceedings{Wang_2026_CVPR, author = {Wang, Shilei and Du, Yipin and Cheng, Yongkang and Lai, Pujian and Gao, Dong and Cheng, Gong}, title = {DCTrack: Divide-and-Conquer for Modality-Missing RGBT Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8338-8345} }
Joint Multi-Camera LiDAR Extrinsic Calibration via Learned Pairwise Initialization and Geometric Refinement: Aziz Al-Najjar,

Marzieh Amini,

James R Green,

Felix Kwamena; [pdf]
[bibtex]
@InProceedings{Al-Najjar_2026_CVPR, author = {Al-Najjar, Aziz and Amini, Marzieh and Green, James R and Kwamena, Felix}, title = {Joint Multi-Camera LiDAR Extrinsic Calibration via Learned Pairwise Initialization and Geometric Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {8229-8237} }