This workshop addresses topics related to image/video/audio quality assessment in machine learning, computer vision, VLM, Diffusion Models, and other types of generative AIs.
Image, video, and audio quality significantly impacts machine learning and computer vision systems, yet remains underexplored by the broader research community. Real-world applications—from streaming services and autonomous vehicles to cashier-less stores and generative AI—critically depend on robust quality assessment and improvement techniques. Despite their importance, most visual learning systems assume high-quality inputs, while in reality, artifacts from capture, compression, transmission, and rendering processes can severely degrade performance and user experience.
This workshop is particularly timely given the explosive growth of generative AI, which introduces new challenges in quality assessment for both inputs and outputs. By bringing together researchers from industry and academia, we aim to systematically investigate how quality issues affect various visual learning tasks and develop innovative assessment and mitigation techniques. Building on the success of our previous workshops at WACV (2022–2026), we expect to stimulate new research directions and attract more talent to this critical field, ultimately improving the robustness and reliability of computer vision applications across industries.