CVPR 2026 Open Access Repository

Mobile AI workshop and associated challenges, 6th edition

Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs: Faraz Kayani,

Sarmad Kayani,

Asad Ahmed,

Radu Timofte,

Dmitry Ignatov; [pdf] [arXiv]
[bibtex]
@InProceedings{Kayani_2026_CVPR, author = {Kayani, Faraz and Kayani, Sarmad and Ahmed, Asad and Timofte, Radu and Ignatov, Dmitry}, title = {Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3792-3800} }
RGB is (Almost) All You Need: Estimating Soil Parameters Using TerraMind: Agata M. Wijata,

Bogdan Ruszczak,

Adriana Niepala,

Lukasz Tulczyjew,

Agata Sage,

Nicolas Longepe,

Jakub Nalepa; [pdf] [supp]
[bibtex]
@InProceedings{Wijata_2026_CVPR, author = {Wijata, Agata M. and Ruszczak, Bogdan and Niepala, Adriana and Tulczyjew, Lukasz and Sage, Agata and Longepe, Nicolas and Nalepa, Jakub}, title = {RGB is (Almost) All You Need: Estimating Soil Parameters Using TerraMind}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3866-3877} }
EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation: Sravanth Kodavanti,

Manjunath Arveti,

Sowmya Vajrala,

Srinivas Miriyala,

Vikram N R; [pdf] [arXiv]
[bibtex]
@InProceedings{Kodavanti_2026_CVPR, author = {Kodavanti, Sravanth and Arveti, Manjunath and Vajrala, Sowmya and Miriyala, Srinivas and R, Vikram N}, title = {EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3801-3809} }
Quantization with Unified Adaptive Distillation to enable multi-LoRA Based One-For-All Generative Vision Models on Edge: Sowmya Vajrala,

Aakash Parmar,

Prasanna R,

Sravanth Kodavanti,

Manjunath Arveti,

Srinivas Soumitri Miriyala,

Ashok Senapati; [pdf] [arXiv]
[bibtex]
@InProceedings{Vajrala_2026_CVPR, author = {Vajrala, Sowmya and Parmar, Aakash and R, Prasanna and Kodavanti, Sravanth and Arveti, Manjunath and Miriyala, Srinivas Soumitri and Senapati, Ashok}, title = {Quantization with Unified Adaptive Distillation to enable multi-LoRA Based One-For-All Generative Vision Models on Edge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3857-3865} }
MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment: Arun Kumar,

Aswathy Baiju,

Radu Timofte,

Dmitry Ignatov; [pdf] [arXiv]
[bibtex]
@InProceedings{Kumar_2026_CVPR, author = {Kumar, Arun and Baiju, Aswathy and Timofte, Radu and Ignatov, Dmitry}, title = {MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3810-3818} }
ZCLIP: Generalization-Aware Compression and Geometry-Preserving Continual Learning for Vision-Language Models on Edge Devices: Kaiqi Zhao,

Yitao Chen; [pdf]
[bibtex]
@InProceedings{Zhao_2026_CVPR, author = {Zhao, Kaiqi and Chen, Yitao}, title = {ZCLIP: Generalization-Aware Compression and Geometry-Preserving Continual Learning for Vision-Language Models on Edge Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3886-3892} }
LiteBokeh: Compact Model for Real-time Bokeh Rendering: Biao Wu,

Yaowei Guo,

Si Gao,

Shaoli Liu,

Chengjian Zheng,

Diankai Zhang,

Ning Wang; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2026_CVPR, author = {Wu, Biao and Guo, Yaowei and Gao, Si and Liu, Shaoli and Zheng, Chengjian and Zhang, Diankai and Wang, Ning}, title = {LiteBokeh: Compact Model for Real-time Bokeh Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3878-3885} }
RealisMobile: High-Fidelity Image Generation and Inference Acceleration System for Mobile Devices using Realistic Vision: Fan Li,

Xiaotong Luo,

Yuan Gao,

Wenjun Zeng; [pdf]
[bibtex]
@InProceedings{Li_2026_CVPR, author = {Li, Fan and Luo, Xiaotong and Gao, Yuan and Zeng, Wenjun}, title = {RealisMobile: High-Fidelity Image Generation and Inference Acceleration System for Mobile Devices using Realistic Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3819-3826} }
Efficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training: Pham Phuong Nam Nguyen,

Nam Tien Le,

Thi Kim Trang Vo,

Nhu Tinh Anh Nguyen; [pdf] [arXiv]
[bibtex]
@InProceedings{Nguyen_2026_CVPR, author = {Nguyen, Pham Phuong Nam and Le, Nam Tien and Vo, Thi Kim Trang and Nguyen, Nhu Tinh Anh}, title = {Efficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3837-3846} }
Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment: Janek Haberer,

Jon Eike Wilhelm,

Olaf Landsiedel; [pdf] [arXiv]
[bibtex]
@InProceedings{Haberer_2026_CVPR, author = {Haberer, Janek and Wilhelm, Jon Eike and Landsiedel, Olaf}, title = {Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3782-3791} }
Bridging the Training-Deployment Gap: Gated Encoding and Multi-Scale Refinement for Efficient Quantization-Aware Image Enhancement: Dat To Thanh,

Nghia Nguyen Trong,

Hoang Vo,

Hieu Bui-Minh,

Tinh-Anh Nguyen-Nhu; [pdf]
[bibtex]
@InProceedings{Thanh_2026_CVPR, author = {Thanh, Dat To and Trong, Nghia Nguyen and Vo, Hoang and Bui-Minh, Hieu and Nguyen-Nhu, Tinh-Anh}, title = {Bridging the Training-Deployment Gap: Gated Encoding and Multi-Scale Refinement for Efficient Quantization-Aware Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3847-3856} }
FastSHADE: Fast Self-augmented Hierarchical Asymmetric Denoising for Efficient Inference on Mobile Devices: Nikolay Falaleev; [pdf] [arXiv]
[bibtex]
@InProceedings{Falaleev_2026_CVPR, author = {Falaleev, Nikolay}, title = {FastSHADE: Fast Self-augmented Hierarchical Asymmetric Denoising for Efficient Inference on Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3772-3781} }
Accelerating On-Device LLM Inference via Activation-guided FFN Distillation on Raspberry Pi: HyeonCheol Moon,

SungHyeon Bae,

Jinwoo Jeong; [pdf] [supp]
[bibtex]
@InProceedings{Moon_2026_CVPR, author = {Moon, HyeonCheol and Bae, SungHyeon and Jeong, Jinwoo}, title = {Accelerating On-Device LLM Inference via Activation-guided FFN Distillation on Raspberry Pi}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {3827-3836} }