Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis in-the-Wild

TL;DR

This paper introduces AM-Adapter, a novel framework for exemplar-based semantic image synthesis in complex scenes, enabling multi-object appearance transfer and improved control using scene-level images and segmentation maps.

Contribution

AM-Adapter is a new learnable model that enhances cross-image matching with semantic information, allowing multi-object appearance transfer in complex scenes, surpassing prior single-object methods.

Findings

Achieves state-of-the-art semantic alignment and appearance fidelity.

Effectively transfers local appearances in multi-object, complex scenes.

Provides controllability for user-defined object placement.

Abstract

Exemplar-based semantic image synthesis generates images aligned with semantic content while preserving the appearance of an exemplar. Conventional structure-guidance models like ControlNet, are limited as they rely solely on text prompts to control appearance and cannot utilize exemplar images as input. Recent tuning-free approaches address this by transferring local appearance via implicit cross-image matching in the augmented self-attention mechanism of pre-trained diffusion models. However, prior works are often restricted to single-object cases or foreground object appearance transfer, struggling with complex scenes involving multiple objects. To overcome this, we propose AM-Adapter (Appearance Matching Adapter) to address exemplar-based semantic image synthesis in-the-wild, enabling multi-object appearance transfer from a single scene-level image. AM-Adapter automatically transfers local appearances from the scene-level input. AM-Adapter alternatively provides controllability to map user-defined object details to specific locations in the synthesized images. Our learnable framework enhances cross-image matching within augmented self-attention by integrating semantic information from segmentation maps. To disentangle generation and matching, we adopt stage-wise training. We first train the structure-guidance and generation networks, followed by training the matching adapter while keeping the others frozen. During inference, we introduce an automated exemplar retrieval method for selecting exemplar image-segmentation pairs efficiently. Despite utilizing minimal learnable parameters, AM-Adapter achieves state-of-the-art performance, excelling in both semantic alignment and local appearance fidelity. Extensive ablations validate our design choices. Code and weights will be released.: https://cvlab-kaist.github.io/AM-Adapter/