We welcome you to CDS-KIAC talk on 13th August 2025 (Wednesday). The details are as below:
Speaker: Raghav Goyal, Researcher at Samsung AI-Center Toronto.
Title: Towards Measuring and Mitigating Hallucinations in Generative Image Super-Resolution
Date and Time: August 13, 2025: 04:00 PM
Venue: #102, CDS Seminar Hall.
Abstract: Generative super-resolution (GSR) currently sets the state-of-the-art in terms of perceptual image quality, overcoming the “regression-to-the-mean” blur of prior non-generative models. However, from a human perspective, such models do not fully conform to the optimal balance between quality and fidelity. Instead, a different class of artifacts, in which generated details fail to perceptually match the low resolution image (LRI) or ground-truth image (GTI), is a critical but under-studied issue in GSR, limiting its practical deployments. In this talk, I will focus on measuring, analyzing, and mitigating these artifacts (i.e., “hallucinations”). First, we analyse hallucinations by observing that they are not well-characterized with existing image metrics or quality models, as they are orthogonal to both exact fidelity and no-reference quality. Second, to measure hallucinations, we propose to take advantage of a multimodal large language model (MLLM) that assesses hallucinatory visual elements and generates a “Hallucination Score” (HS) which is closely aligned with human evaluations. Third, to mitigate hallucinations, we find that certain deep feature distances have strong correlations with HS, and therefore we propose to align the GSR models by using such features as differentiable reward functions to mitigate hallucinations.
Bio of Speaker: Raghav Goyal is a researcher at Samsung AI-Center Toronto. He obtained his PhD at University of British Columbia (UBC) supervised by Prof. Leonid Sigal with a focus on data-efficient learning for structured vision tasks. Prior to this, he spent three years at a startup named “20bn” (now at Qualcomm Research) working on video understanding including Something-Something dataset. He has published in top venues such as CVPR, ICCV and NeurIPS, with internships at Google, Meta, and Xerox Research. He obtained an Integrated M.Tech. (5-year programme) from Indian Institute of Technology (IIT) Delhi in Mathematics and Computing.
Host Faculty: Prof. Venkatesh Babu
ALL ARE WELCOME
