📝 Abstract:
Conventional imaging sensors often struggle to capture the full dynamic range of real-world scenes, leading to a loss of detail in shadows and highlights. This talk presents a holistic approach to overcoming these limitations by aligning alternative hardware designs, such as multi-exposure sensors, with robust machine-learning solutions. The research demonstrates that capturing varied exposures at the pixel level provides critical reference data to simplify complex tasks like denoising and high-dynamic-range (HDR) reconstruction. These benefits extend to the temporal domain, where motion blur information is utilized to handle complex, non-uniform motion and enable high-quality video frame interpolation for HDR content. Complementing these reconstruction techniques is the challenge of perceptually meaningful quality evaluation, which can be improved by leveraging visual masking—a fundamental characteristic of the human visual system. The presentation highlights how modeling masking effects significantly enhances the alignment of traditional metrics (PSNR, SSIM) and modern learning-based models (LPIPS, DISTS) with human perception. Building on this methodology, this talk introduces MILO, a lightweight, multiscale perceptual metric. Trained via pseudo-MOS supervision, MILO achieves state-of-the-art accuracy and serves as an effective perceptual loss for image and latent-space optimization within generative pipelines like Stable Diffusion, significantly improving performance in various image restoration tasks.
👥 Biography:
Uğur Çoğalan received his B.Sc. degree from Middle East Technical University (METU) in 2016 and his M.Sc. degree in 2019 under the supervision of Prof. Ahmet Oğuz Akyüz. Most recently, he completed his Ph.D. at the Max Planck Institute for Informatics and Saarland University under the supervision of Prof. Karol Myszkowski, followed by a one-year postdoctoral position at the same institute. His postdoctoral research resulted in a SIGGRAPH Asia 2025 paper, which was recognized with an Honorable Mention Award. His research focus lies in perceptually-aware image quality metrics, HDR video and imaging, and image restoration and enhancement.