Creative domains play a vital role in modern society, shaping cultural life but also the economy and social dynamics. With the rapid advancement of generative AI and computer vision technologies, these fields are undergoing transformative changes, from enhancing artistic content retrieval, fashion, and curation to enabling synthetic media generation and novel artistic methods. The rise of creative platforms where communities develop, share, and assemble tools and systems for artistic creation is opening the doors to new forms of art, collaborations, and production of new types of media.
In addition, online fashion retail has gained popularity in the past decade, allowing customers to browse vast product selections without visiting multiple stores or enduring long checkout lines. Computer vision and AI are poised to revolutionize the fashion industry by enhancing customer experiences. Moreover, the emergence of social media offers exciting opportunities for fashion exploration in unprecedented ways. These developments pose compelling challenges for the machine learning and computer vision research communities. At the same time, creative AI technologies raise important ethical concerns, including representational harms related to data augmentation, generation, and the analysis of culturally sensitive content.
Our goal is to foster interdisciplinary discussions among researchers and practitioners in computer vision and machine learning, as well as artists, designers, sociotechnical researchers, policymakers, social scientists, and other cultural stakeholders. By creating a collaborative space, we aim to address complex challenges that arise at the intersection of generative AI, creativity, and ethics. Specifically, this workshop will encourage methodological work on the applications of computer vision technologies in art, fashion, retail, and design, generative art presentations and methodological advancements, retrospective discussions, position papers examining the societal impacts of creative AI applications such as cultural appropriation, environmental consequences of generative art, biases in AI-generated art. We welcome technical contributions in computer vision for fashion and creative content generation.
This year, we introduce an Art Gallery submission track with a participatory selection process to further engage the community. By bringing together a diverse set of researchers and practitioners in computer vision, fashion, art, and design, this workshop seeks to advance interdisciplinary discourse and foster collaboration across these domains. We aim to sustain and deepen conversations among professionals in fashion, art, and AI, ensuring a collective effort to tackle these evolving challenges.
LawZero
EBB
Simon Hudson
Botto DAO
08:45 - 08:50 Opening remarks
08:50 - 09:30 Keynote Talk by Ira Kemelmacher-Shlizerman, Allen School, Univ. Washington, and Google : "“Virtual Try-on for Billions of People “
09:30 - 10:30 Accepted paper spotlights
Dress-up: Generating Animatable Clothed 3D Humans via Latent Modeling of 3D Gaussian Texture Maps
LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing
PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask
10:30 - 11:00 Keynote Talk by Shawn Shan, Dartmouth College:"Protecting and Empowering Stakeholders in Today’s AI ecosystem".
11:00 - 11.20 Coffee and Social Event
11.20 - 12:00 Keynote Talk by Iro Armeni, Stanford University: "Designing with What We Have: Generative AI for Reuse in Interiors".
12:00 - 13:00 Panel Discussion on Creative AI.
For general questions regarding the workshop, please contact the organizers at this email.
The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.