Computer Vision for Developing Countries

FLD+: Data-efficient Evaluation Metric for Generative Models

Pranav Jeevan,

Neeraj Nixon,

Amit Sethi

[pdf] [supp]

[bibtex]

@InProceedings{Jeevan_2025_ICCV, author = {Jeevan, Pranav and Nixon, Neeraj and Sethi, Amit}, title = {FLD+: Data-efficient Evaluation Metric for Generative Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {1649-1657} }

V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?

Natchapon Jongwiriyanurak,

Zichao Zeng,

June Moh Goo,

Xinglei Wang,

Ilya Ilyankou,

Kerkritt Sriroongvikrai,

Nicola Christie,

Meihui Wang,

Huanfa Chen,

James Haworth

[pdf] [supp]

[bibtex]

@InProceedings{Jongwiriyanurak_2025_ICCV, author = {Jongwiriyanurak, Natchapon and Zeng, Zichao and Goo, June Moh and Wang, Xinglei and Ilyankou, Ilya and Sriroongvikrai, Kerkritt and Christie, Nicola and Wang, Meihui and Chen, Huanfa and Haworth, James}, title = {V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {1658-1667} }

WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting

Pranav Jeevan,

Dharshan Sampath Kumar,

Amit Sethi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jeevan_2025_ICCV, author = {Jeevan, Pranav and Kumar, Dharshan Sampath and Sethi, Amit}, title = {WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {1639-1648} }

Nayana: A Foundation for Document-Centric Vision-Language Models via Multi-Task, Multimodal, and Multilingual Data Synthesis

Adithya S Kolavi,

Samarth P,

Vyoman Jain

[pdf] [supp]

[bibtex]

@InProceedings{Kolavi_2025_ICCV, author = {Kolavi, Adithya S and P, Samarth and Jain, Vyoman}, title = {Nayana: A Foundation for Document-Centric Vision-Language Models via Multi-Task, Multimodal, and Multilingual Data Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {1678-1687} }

Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception

Moseli Mots'oehli,

Feimei Chen,

Hok Wai Chan,

Itumeleng Victor Tlali,

Thulani Babeli,

Kyungim Baek,

Huaijin Chen

[pdf] [arXiv]

[bibtex]

@InProceedings{Mots'oehli_2025_ICCV, author = {Mots'oehli, Moseli and Chen, Feimei and Chan, Hok Wai and Tlali, Itumeleng Victor and Babeli, Thulani and Baek, Kyungim and Chen, Huaijin}, title = {Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {1668-1677} }