Panoptic Pairwise Distortion Graph
For researchers in image quality assessment and multimodal AI, this work opens a new direction for fine-grained, structured pairwise image comparison, but the gains are demonstrated only on the proposed benchmark.
The paper introduces a new task, Distortion Graph (DG), for structured pairwise image assessment at the region level, and provides a dataset (PandaSet), benchmark (PandaBench), and model (Panda). The proposed approach reveals that current MLLMs struggle with region-level degradation understanding, while training on PandaSet or prompting with DG improves performance.
In this work, we introduce a new perspective on comparative image assessment by representing an image pair as a structured composition of its regions. In contrast, existing methods focus on whole image analysis, while implicitly relying on region-level understanding. We extend the intra-image notion of a scene graph to inter-image, and propose a novel task of Distortion Graph (DG). DG treats paired images as a structured topology grounded in regions, and represents dense degradation information such as distortion type, severity, comparison and quality score in a compact interpretable graph structure. To realize the task of learning a distortion graph, we contribute (i) a region-level dataset, PandaSet, (ii) a benchmark suite, PandaBench, with varying region-level difficulty, and (iii) an efficient architecture, Panda, to generate distortion graphs. We demonstrate that PandaBench poses a significant challenge for state-of-the-art multimodal large language models (MLLMs) as they fail to understand region-level degradations even when fed with explicit region cues. We show that training on PandaSet or prompting with DG elicits region-wise distortion understanding, opening a new direction for fine-grained, structured pairwise image assessment.