DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data

TL;DR

DreamSim is a new perceptual similarity metric trained on synthetic data that better aligns with human judgments, capturing semantic content, layout, and object pose, and generalizes well to real images.

Contribution

We introduce DreamSim, a perceptual metric trained on synthetic image pairs that captures mid-level visual features and aligns closely with human perception.

Findings

DreamSim outperforms existing metrics on retrieval tasks.

It generalizes effectively from synthetic to real images.

It emphasizes semantic content and layout in similarity assessments.

Abstract

Current perceptual similarity metrics operate at the level of pixels and patches. These metrics compare images in terms of their low-level colors and textures, but fail to capture mid-level similarities and differences in image layout, object pose, and semantic content. In this paper, we develop a perceptual metric that assesses images holistically. Our first step is to collect a new dataset of human similarity judgments over image pairs that are alike in diverse ways. Critical to this dataset is that judgments are nearly automatic and shared by all observers. To achieve this we use recent text-to-image models to create synthetic pairs that are perturbed along various dimensions. We observe that popular perceptual metrics fall short of explaining our new data, and we introduce a new metric, DreamSim, tuned to better align with human perception. We analyze how our metric is affected by different visual attributes, and find that it focuses heavily on foreground objects and semantic content while also being sensitive to color and layout. Notably, despite being trained on synthetic data, our metric generalizes to real images, giving strong results on retrieval and reconstruction tasks. Furthermore, our metric outperforms both prior learned metrics and recent large vision models on these tasks.