The reviewed record of science sign in
Pith

arxiv: 2208.13753 · v2 · pith:3ZJAHGJM · submitted 2022-08-29 · cs.CV · cs.AI· cs.LG

Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:3ZJAHGJMrecord.jsonopen to challenge →

classification cs.CV cs.AIcs.LG
keywords imagesynthesisfridococodiffusioncoarse-to-finecomplexconditional
0
0 comments X
read the original abstract

Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stage, additional input conditions like text, scene graph, or image layout can be further exploited. Thus, Frido can be also applied for conditional or cross-modality image synthesis. We conduct extensive experiments over various unconditioned and conditional image generation tasks, ranging from text-to-image synthesis, layout-to-image, scene-graph-to-image, to label-to-image. More specifically, we achieved state-of-the-art FID scores on five benchmarks, namely layout-to-image on COCO and OpenImages, scene-graph-to-image on COCO and Visual Genome, and label-to-image on COCO. Code is available at https://github.com/davidhalladay/Frido.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.