ICCV 2025 Open Access Repository

Vision Foundation Models and Generative AI for Accessibility: Challenges and Opportunities

RampNet: A Two-Stage Pipeline for Bootstrapping Curb Ramp Detection in Streetscape Images from Open Government Metadata: John S. O'Meara,

Jared Hwang,

Zeyu Wang,

Michael Saugstad,

Jon E. Froehlich; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{O'Meara_2025_ICCV, author = {O'Meara, John S. and Hwang, Jared and Wang, Zeyu and Saugstad, Michael and Froehlich, Jon E.}, title = {RampNet: A Two-Stage Pipeline for Bootstrapping Curb Ramp Detection in Streetscape Images from Open Government Metadata}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {6656-6665} }
Introduction to the First Workshop on Vision Foundation Models and Generative AI for Accessibility: Yapeng Tian,

Yuhang Zhao,

Jon E. Froehlich,

Chu Li,

Yuheng Wu; [pdf]
[bibtex]
@InProceedings{Tian_2025_ICCV, author = {Tian, Yapeng and Zhao, Yuhang and Froehlich, Jon E. and Li, Chu and Wu, Yuheng}, title = {Introduction to the First Workshop on Vision Foundation Models and Generative AI for Accessibility}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {6694-6703} }
VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis: Alexandre Symeonidis-Herzig,

Ozge Mercanoglu Sincan,

Richard Bowden; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Symeonidis-Herzig_2025_ICCV, author = {Symeonidis-Herzig, Alexandre and Sincan, Ozge Mercanoglu and Bowden, Richard}, title = {VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {6666-6675} }
The Escalator Problem: Identifying Implicit Motion Blindness in AI for Accessibility: Xiantao Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Xiantao}, title = {The Escalator Problem: Identifying Implicit Motion Blindness in AI for Accessibility}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {6635-6643} }
Seeing in 2D, Thinking in 3D: 3D Hand Mesh-Guided Feature Learning for Continuous Fingerspelling: Katerina Papadimitriou,

Panagiotis Filntisis,

George Retsinas,

Gerasimos Potamianos,

Petros Maragos; [pdf]
[bibtex]
@InProceedings{Papadimitriou_2025_ICCV, author = {Papadimitriou, Katerina and Filntisis, Panagiotis and Retsinas, George and Potamianos, Gerasimos and Maragos, Petros}, title = {Seeing in 2D, Thinking in 3D: 3D Hand Mesh-Guided Feature Learning for Continuous Fingerspelling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {6676-6685} }
SignLLM: Sign Language Production Large Language Models: Sen Fang,

Chen Chen,

Lei Wang,

Ce Zheng,

Chunyu Sui,

Yapeng Tian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fang_2025_ICCV, author = {Fang, Sen and Chen, Chen and Wang, Lei and Zheng, Ce and Sui, Chunyu and Tian, Yapeng}, title = {SignLLM: Sign Language Production Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {6622-6634} }
Who's Asking? Investigating Bias Through the Lens of Disability-Framed Queries in LLMs: Vishnu Hari,

Kalpana Panda,

Srikant Panda,

Amit Agarwal,

Hitesh Laxmichand Patel; [pdf]
[bibtex]
@InProceedings{Hari_2025_ICCV, author = {Hari, Vishnu and Panda, Kalpana and Panda, Srikant and Agarwal, Amit and Patel, Hitesh Laxmichand}, title = {Who's Asking? Investigating Bias Through the Lens of Disability-Framed Queries in LLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {6644-6655} }
Automated Context-Aware Navigation Support for Individuals with Visual Impairment Using Multimodal Language Models in Urban Environments: Alton Chao,

Erika Maquiling,

Edmund Chao,

Roshan Sanjeev,

Tonko Bossen,

Ross Greer; [pdf]
[bibtex]
@InProceedings{Chao_2025_ICCV, author = {Chao, Alton and Maquiling, Erika and Chao, Edmund and Sanjeev, Roshan and Bossen, Tonko and Greer, Ross}, title = {Automated Context-Aware Navigation Support for Individuals with Visual Impairment Using Multimodal Language Models in Urban Environments}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {6686-6693} }