CVPR 2026 Open Access Repository

Efficient Deep Learning for Computer Vision

OP-LoRA: The Blessing of Dimensionality with Overparameterized Low-Rank Adaptation: Piotr Teterwak,

Kate Saenko,

Bryan A. Plummer,

Ser-Nam Lim; [pdf] [supp]
[bibtex]
@InProceedings{Teterwak_2026_CVPR, author = {Teterwak, Piotr and Saenko, Kate and Plummer, Bryan A. and Lim, Ser-Nam}, title = {OP-LoRA: The Blessing of Dimensionality with Overparameterized Low-Rank Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3643-3653} }
Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models: Pranav A,

Shashank B,

Pranav Siddappa,

Dominik Seuss,

Minal Moharir,

Subramanya KN; [pdf] [arXiv]
[bibtex]
@InProceedings{A_2026_CVPR, author = {A, Pranav and B, Shashank and Siddappa, Pranav and Seuss, Dominik and Moharir, Minal and KN, Subramanya}, title = {Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3479-3487} }
FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices: Shizhong Han,

Hsin-Pai Cheng,

Hong Cai,

Jihad Marsi,

Soyeb Nagori,

Fatih Porikli; [pdf] [arXiv]
[bibtex]
@InProceedings{Han_2026_CVPR, author = {Han, Shizhong and Cheng, Hsin-Pai and Cai, Hong and Marsi, Jihad and Nagori, Soyeb and Porikli, Fatih}, title = {FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3518-3528} }
Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity: Navin Ranjan,

Andreas Savakis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ranjan_2026_CVPR, author = {Ranjan, Navin and Savakis, Andreas}, title = {Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3599-3609} }
PointTransformerX: Portable and Efficient 3D Point Cloud Processing without Sparse Algorithms: Laurenz Reichardt,

Nikolas Ebert,

Oliver Wasenmüller; [pdf]
[bibtex]
@InProceedings{Reichardt_2026_CVPR, author = {Reichardt, Laurenz and Ebert, Nikolas and Wasenm\"uller, Oliver}, title = {PointTransformerX: Portable and Efficient 3D Point Cloud Processing without Sparse Algorithms}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3610-3619} }
Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation: Quoc-Huy Trinh,

Mustapha Abdullahi,

Bo Zhao,

Debesh Jha; [pdf] [arXiv]
[bibtex]
@InProceedings{Trinh_2026_CVPR, author = {Trinh, Quoc-Huy and Abdullahi, Mustapha and Zhao, Bo and Jha, Debesh}, title = {Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3654-3663} }
Understanding Pruning Regimes in Vision-Language Models through Domain-Aware Layer Selection: Saeed Khaki,

Nima Safaei,

Kamal Ginotra; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khaki_2026_CVPR, author = {Khaki, Saeed and Safaei, Nima and Ginotra, Kamal}, title = {Understanding Pruning Regimes in Vision-Language Models through Domain-Aware Layer Selection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3549-3558} }
How Should Video LLMs Output Time? An Analysis of Efficient Temporal Grounding Paradigms: Shengji Jin,

Yuanhao Zou,

Victor Zhu,

Zhengping Ji,

Chen Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2026_CVPR, author = {Jin, Shengji and Zou, Yuanhao and Zhu, Victor and Ji, Zhengping and Chen, Chen}, title = {How Should Video LLMs Output Time? An Analysis of Efficient Temporal Grounding Paradigms}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3539-3548} }
LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment: Katarzyna Fojcik,

Renaldas Zioma,

Jogundas Armaitis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fojcik_2026_CVPR, author = {Fojcik, Katarzyna and Zioma, Renaldas and Armaitis, Jogundas}, title = {LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3498-3507} }
Mitigating Token Homogenization in Token Merging via Source Selection Switching and Merge Embedding: Yuki Ichikawa,

Tatsuya Kaneko,

Masato Motomura,

Daichi Fujiki; [pdf]
[bibtex]
@InProceedings{Ichikawa_2026_CVPR, author = {Ichikawa, Yuki and Kaneko, Tatsuya and Motomura, Masato and Fujiki, Daichi}, title = {Mitigating Token Homogenization in Token Merging via Source Selection Switching and Merge Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3529-3538} }
SWIFT: Efficient Warping-Only Optical Flow via Scale-Specialized Refinement: Robert J. Wang,

Charles X. Ling; [pdf]
[bibtex]
@InProceedings{Wang_2026_CVPR, author = {Wang, Robert J. and Ling, Charles X.}, title = {SWIFT: Efficient Warping-Only Optical Flow via Scale-Specialized Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3674-3682} }
Fixing Quantization with Lightweight Adapters: Mohammadreza Mohammadi,

Matthew Grenier,

Ramtin Zand; [pdf]
[bibtex]
@InProceedings{Mohammadi_2026_CVPR, author = {Mohammadi, Mohammadreza and Grenier, Matthew and Zand, Ramtin}, title = {Fixing Quantization with Lightweight Adapters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3569-3578} }
The Space Between Sensing and Processing: In-Sensor and Near-Sensor Computing for Embedded Vision Systems: Mohammadreza Mohammadi,

Lily Lamb,

Aishneet Juneja,

Sepehr Tabrizchi,

Deniz Najafi,

Shaahin Angizi,

Arman Roohi,

Ramtin Zand; [pdf]
[bibtex]
@InProceedings{Mohammadi_2026_CVPR, author = {Mohammadi, Mohammadreza and Lamb, Lily and Juneja, Aishneet and Tabrizchi, Sepehr and Najafi, Deniz and Angizi, Shaahin and Roohi, Arman and Zand, Ramtin}, title = {The Space Between Sensing and Processing: In-Sensor and Near-Sensor Computing for Embedded Vision Systems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3579-3588} }
PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders: Niccolò Cavagnero,

Narges Norouzi,

Gijs Dubbelman,

Daan de Geus; [pdf] [arXiv]
[bibtex]
@InProceedings{Cavagnero_2026_CVPR, author = {Cavagnero, Niccol\`o and Norouzi, Narges and Dubbelman, Gijs and de Geus, Daan}, title = {PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3488-3497} }
MetaDepth-CPU: Zero-Shot Monocular Depth Estimation for Edge Devices: Marc Mapeke,

Zaiwei Zhang,

Wei Ye,

Rakesh Ranjan,

JQ Huang; [pdf]
[bibtex]
@InProceedings{Mapeke_2026_CVPR, author = {Mapeke, Marc and Zhang, Zaiwei and Ye, Wei and Ranjan, Rakesh and Huang, JQ}, title = {MetaDepth-CPU: Zero-Shot Monocular Depth Estimation for Edge Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3559-3568} }
LightMedSeg: Lightweight 3D Medical Image Segmentation with Learned Spatial Anchors: Kavyansh Tyagi,

Vishwas Rathi,

Puneet Goyal; [pdf] [arXiv]
[bibtex]
@InProceedings{Tyagi_2026_CVPR, author = {Tyagi, Kavyansh and Rathi, Vishwas and Goyal, Puneet}, title = {LightMedSeg: Lightweight 3D Medical Image Segmentation with Learned Spatial Anchors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3664-3673} }
Temporal Cluster Assignment for Efficient Real-Time Video Segmentation: Ka-Wai Yung,

Felix J. S. Bragman,

Jialang Xu,

Imanol Luengo,

Danail Stoyanov,

Evangelos B. Mazomenos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yung_2026_CVPR, author = {Yung, Ka-Wai and Bragman, Felix J. S. and Xu, Jialang and Luengo, Imanol and Stoyanov, Danail and Mazomenos, Evangelos B.}, title = {Temporal Cluster Assignment for Efficient Real-Time Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3693-3702} }
Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction: Patrick Glandorf,

Thomas Norrenbrock,

Bodo Rosenhahn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Glandorf_2026_CVPR, author = {Glandorf, Patrick and Norrenbrock, Thomas and Rosenhahn, Bodo}, title = {Video Patch Pruning: Efficient Video Instance Segmentation via Early Token Reduction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3508-3517} }
VDPP: Video Depth Post-Processing for Speed and Scalability: Daewon Yoon,

Injun Baek,

Sangyu Han,

Yearim Kim,

Nojun Kwak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoon_2026_CVPR, author = {Yoon, Daewon and Baek, Injun and Han, Sangyu and Kim, Yearim and Kwak, Nojun}, title = {VDPP: Video Depth Post-Processing for Speed and Scalability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3683-3692} }
Training a Student Expert via Semi-Supervised Foundation Model Distillation: Pardis Taghavi,

Tian Liu,

Renjie Li,

Reza Langari,

Zhengzhong Tu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Taghavi_2026_CVPR, author = {Taghavi, Pardis and Liu, Tian and Li, Renjie and Langari, Reza and Tu, Zhengzhong}, title = {Training a Student Expert via Semi-Supervised Foundation Model Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3620-3630} }
Image Hashing via Cross-View Code Alignment in the Age of Foundation Models: Ilyass Moummad,

Kawtar Zaher,

Hervé Goëau,

Alexis Joly; [pdf] [arXiv]
[bibtex]
@InProceedings{Moummad_2026_CVPR, author = {Moummad, Ilyass and Zaher, Kawtar and Go\"eau, Herv\'e and Joly, Alexis}, title = {Image Hashing via Cross-View Code Alignment in the Age of Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3589-3598} }
AdaVTG-LLM: A VideoLLM-Based Efficient Video Temporal Grounding Framework: Te Tao,

Shao-Lun Huang; [pdf]
[bibtex]
@InProceedings{Tao_2026_CVPR, author = {Tao, Te and Huang, Shao-Lun}, title = {AdaVTG-LLM: A VideoLLM-Based Efficient Video Temporal Grounding Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3631-3642} }