ICCV 2025 Open Access Repository

The 2nd Workshop on Efficient Computing under Limited Resources: Visual Computing

FDAL: Leveraging Feature Distillation for Efficient and Task-Aware Active Learning: Rebati Gaire,

Arman Roohi; [pdf]
[bibtex]
@InProceedings{Gaire_2025_ICCV, author = {Gaire, Rebati and Roohi, Arman}, title = {FDAL: Leveraging Feature Distillation for Efficient and Task-Aware Active Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3131-3138} }
Latent Representation of Microstructures using Variational Autoencoders with Spatial Statistics Space Loss: Andy Cai,

Sayed Sajad Hashemi,

Noah Paulson,

Michael Guerzhoy; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2025_ICCV, author = {Cai, Andy and Hashemi, Sayed Sajad and Paulson, Noah and Guerzhoy, Michael}, title = {Latent Representation of Microstructures using Variational Autoencoders with Spatial Statistics Space Loss}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3124-3130} }
L-GGSC: Learnable Graph-based Gaussian Splatting Compression: Akihiro Kuwabara,

Hinata Kirihara,

Sorachi Kato,

Toshiaki Koike-Akino,

Takuya Fujihashi; [pdf]
[bibtex]
@InProceedings{Kuwabara_2025_ICCV, author = {Kuwabara, Akihiro and Kirihara, Hinata and Kato, Sorachi and Koike-Akino, Toshiaki and Fujihashi, Takuya}, title = {L-GGSC: Learnable Graph-based Gaussian Splatting Compression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3057-3063} }
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics: Alex Colagrande,

Paul Caillon,

Eva Feillet,

Alexandre Allauzen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Colagrande_2025_ICCV, author = {Colagrande, Alex and Caillon, Paul and Feillet, Eva and Allauzen, Alexandre}, title = {Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3099-3108} }
Tiny-vGamba: Distilling Large Vision-(Language) Knowledge from CLIP into a Lightweight vGamba Network: Yunusa Haruna,

Adamu Lawan,

Ismail Abdulrashid,

Abdulganiyu Abdu Yusuf; [pdf]
[bibtex]
@InProceedings{Haruna_2025_ICCV, author = {Haruna, Yunusa and Lawan, Adamu and Abdulrashid, Ismail and Yusuf, Abdulganiyu Abdu}, title = {Tiny-vGamba: Distilling Large Vision-(Language) Knowledge from CLIP into a Lightweight vGamba Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3083-3091} }
Your Super Resolution Model is not Enough for Tackling Real-World Scenarios: Dongsik Yoon,

Jongeun Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoon_2025_ICCV, author = {Yoon, Dongsik and Kim, Jongeun}, title = {Your Super Resolution Model is not Enough for Tackling Real-World Scenarios}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3092-3098} }
Leveraging Learned Image Prior for 3D Gaussian Compression: Seungjoo Shin,

Jaesik Park,

Sunghyun Cho; [pdf] [arXiv]
[bibtex]
@InProceedings{Shin_2025_ICCV, author = {Shin, Seungjoo and Park, Jaesik and Cho, Sunghyun}, title = {Leveraging Learned Image Prior for 3D Gaussian Compression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3047-3056} }
Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation: Patrick Glandorf,

Bodo Rosenhahn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Glandorf_2025_ICCV, author = {Glandorf, Patrick and Rosenhahn, Bodo}, title = {Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3006-3016} }
From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting: Hung Nguyen,

An Le,

Blark Runfa Li,

Truong Nguyen; [pdf] [arXiv]
[bibtex]
@InProceedings{Nguyen_2025_ICCV, author = {Nguyen, Hung and Le, An and Li, Blark Runfa and Nguyen, Truong}, title = {From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3139-3148} }
ECLR'25: 2nd Workshop on Efficient Computing under Limited Resources: Visual Computing: Jinyang Guo,

Zhenghao Chen,

Yuqing Ma,

Yifu Ding,

Xianglong Liu,

Jinman Kim,

Wanli Ouyang,

Dacheng Tao; [pdf]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Jinyang and Chen, Zhenghao and Ma, Yuqing and Ding, Yifu and Liu, Xianglong and Kim, Jinman and Ouyang, Wanli and Tao, Dacheng}, title = {ECLR'25: 2nd Workshop on Efficient Computing under Limited Resources: Visual Computing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3158-3161} }
From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Prediction: Chihiro Noguchi,

Takaki Yamamoto; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Noguchi_2025_ICCV, author = {Noguchi, Chihiro and Yamamoto, Takaki}, title = {From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3073-3082} }
Fisheye image augmentation for overcoming domain gaps with the limited dataset: Hyeseong Lee,

Sunmin Park,

Miyoung Lee; [pdf]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Hyeseong and Park, Sunmin and Lee, Miyoung}, title = {Fisheye image augmentation for overcoming domain gaps with the limited dataset}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3064-3072} }
Low-bit FlashAttention Accelerated Operator Design Based on Triton: Jinyang Du,

Jinyang Guo,

Yifu Ding; [pdf]
[bibtex]
@InProceedings{Du_2025_ICCV, author = {Du, Jinyang and Guo, Jinyang and Ding, Yifu}, title = {Low-bit FlashAttention Accelerated Operator Design Based on Triton}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2996-3005} }
Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedure: Minghao Yang,

Pengyuan Li,

Linlin Gao,

Zhiying Cui,

Wenbo Li,

Jiangjian Xiao; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Minghao and Li, Pengyuan and Gao, Linlin and Cui, Zhiying and Li, Wenbo and Xiao, Jiangjian}, title = {Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedure}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3117-3123} }
Adaptive Compression of Large Vision Models for Efficient Image Quality Assessment of AI-Generated Content: Shivam Bhardwaj,

Tushar Shinde; [pdf]
[bibtex]
@InProceedings{Bhardwaj_2025_ICCV, author = {Bhardwaj, Shivam and Shinde, Tushar}, title = {Adaptive Compression of Large Vision Models for Efficient Image Quality Assessment of AI-Generated Content}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3109-3116} }
VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation: Mustafa Munir,

Alex Zhang,

Radu Marculescu; [pdf] [arXiv]
[bibtex]
@InProceedings{Munir_2025_ICCV, author = {Munir, Mustafa and Zhang, Alex and Marculescu, Radu}, title = {VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3037-3046} }
Compressed Diffusion: Pruning with Knowledge Distillation for Efficient Text-to-Image Generation: Nasrin Kalanat,

Ohiremen Dibua,

Yan Kang,

Yifang Gong,

Xiaowei Jia; [pdf]
[bibtex]
@InProceedings{Kalanat_2025_ICCV, author = {Kalanat, Nasrin and Dibua, Ohiremen and Kang, Yan and Gong, Yifang and Jia, Xiaowei}, title = {Compressed Diffusion: Pruning with Knowledge Distillation for Efficient Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3149-3157} }
Kernel-based Motion Free B-frame Coding for Neural Video Compression: Thang Van Nguyen; [pdf]
[bibtex]
@InProceedings{Van_Nguyen_2025_ICCV, author = {Van Nguyen, Thang}, title = {Kernel-based Motion Free B-frame Coding for Neural Video Compression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3017-3025} }
Efficient Depth- and Spatially-Varying Image Simulation for Defocus Deblur: Xinge Yang,

Chuong Nguyen,

Wenbin Wang,

Kaizhang Kang,

Wolfgang Heidrich,

Xiaoxing Li; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Xinge and Nguyen, Chuong and Wang, Wenbin and Kang, Kaizhang and Heidrich, Wolfgang and Li, Xiaoxing}, title = {Efficient Depth- and Spatially-Varying Image Simulation for Defocus Deblur}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {3026-3036} }