Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis

• URL: http://arxiv.org/abs/2412.03150v1
• Date: Wed, 04 Dec 2024 09:17:47 GMT
• Title: Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis
• Authors: Siyoon Jin, Jisu Nam, Jiyoung Kim, Dahyun Chung, Yeong-Seok Kim, Joonhyung Park, Heonjeong Chu, Seungryong Kim,
• Abstract summary: Exemplar-based semantic image synthesis aims to generate images aligned with given semantic content while preserving the appearance of an exemplar image. Recent tuning-free approaches address this limitation by transferring local appearance from the exemplar image to the synthesized image. We propose the Appearance Matching Adapter (AM-Adapter), a learnable framework that enhances cross-image matching within augmented self-attention.
• Score: 29.23745176017559
• License:
• Abstract: Exemplar-based semantic image synthesis aims to generate images aligned with given semantic content while preserving the appearance of an exemplar image. Conventional structure-guidance models, such as ControlNet, are limited in that they cannot directly utilize exemplar images as input, relying instead solely on text prompts to control appearance. Recent tuning-free approaches address this limitation by transferring local appearance from the exemplar image to the synthesized image through implicit cross-image matching in the augmented self-attention mechanism of pre-trained diffusion models. However, these methods face challenges when applied to content-rich scenes with significant geometric deformations, such as driving scenes. In this paper, we propose the Appearance Matching Adapter (AM-Adapter), a learnable framework that enhances cross-image matching within augmented self-attention by incorporating semantic information from segmentation maps. To effectively disentangle generation and matching processes, we adopt a stage-wise training approach. Initially, we train the structure-guidance and generation networks, followed by training the AM-Adapter while keeping the other networks frozen. During inference, we introduce an automated exemplar retrieval method to efficiently select exemplar image-segmentation pairs. Despite utilizing a limited number of learnable parameters, our method achieves state-of-the-art performance, excelling in both semantic alignment preservation and local appearance fidelity. Extensive ablation studies further validate our design choices. Code and pre-trained weights will be publicly available.: https://cvlab-kaist.github.io/AM-Adapter/

Related papers

• Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks [53.67497327319569]
  We introduce a novel neural rendering technique to solve image-to-3D from a single view. Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks. Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
  arXiv  Detail & Related papers  (2023-12-24T08:42:37Z)
• Cross-Image Attention for Zero-Shot Appearance Transfer [68.43651329067393]
  We introduce a cross-image attention mechanism that implicitly establishes semantic correspondences across images. We harness three mechanisms that either manipulate the noisy latent codes or the model's internal representations throughout the denoising process. Experiments show that our method is effective across a wide range of object categories and is robust to variations in shape, size, and viewpoint.
  arXiv  Detail & Related papers  (2023-11-06T18:33:24Z)
• Dense Text-to-Image Generation with Attention Modulation [49.287458275920514]
  Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions. We propose DenseDiffusion, a training-free method that adapts a pre-trained text-to-image model to handle such dense captions. We achieve similar-quality visual results with models specifically trained with layout conditions.
  arXiv  Detail & Related papers  (2023-08-24T17:59:01Z)
• Zero-shot spatial layout conditioning for text-to-image diffusion models [52.24744018240424]
  Large-scale text-to-image diffusion models have significantly improved the state of the art in generative image modelling. We consider image generation from text associated with segments on the image canvas, which combines an intuitive natural language interface with precise spatial control over the generated content. We propose ZestGuide, a zero-shot segmentation guidance approach that can be plugged into pre-trained text-to-image diffusion models.
  arXiv  Detail & Related papers  (2023-06-23T19:24:48Z)
• Masked and Adaptive Transformer for Exemplar Based Image Translation [16.93344592811513]
  Cross-domain semantic matching is challenging. We propose a masked and adaptive transformer (MAT) for learning accurate cross-domain correspondence. We devise a novel contrastive style learning method, for acquire quality-discriminative style representations.
  arXiv  Detail & Related papers  (2023-03-30T03:21:14Z)
• Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis [68.1281982092765]
  We propose a novel normalization module, termed as REtrieval-based Spatially AdaptIve normaLization (RESAIL) RESAIL provides pixel level fine-grained guidance to the normalization architecture. Experiments on several challenging datasets show that our RESAIL performs favorably against state-of-the-arts in terms of quantitative metrics, visual quality, and subjective evaluation.
  arXiv  Detail & Related papers  (2022-04-06T14:21:39Z)
• Image Shape Manipulation from a Single Augmented Training Sample [26.342929563689218]
  DeepSIM is a generative model for conditional image manipulation based on a single image. Our network learns to map between a primitive representation of the image to the image itself.
  arXiv  Detail & Related papers  (2021-09-13T17:44:04Z)
• Image Shape Manipulation from a Single Augmented Training Sample [24.373900721120286]
  DeepSIM is a generative model for conditional image manipulation based on a single image. Our network learns to map between a primitive representation of the image to the image itself.
  arXiv  Detail & Related papers  (2020-07-02T17:55:27Z)
• Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision [83.33283892171562]
  Example-guided image synthesis has recently been attempted to synthesize an image from a semantic label map and an exemplary image. In this paper, we tackle a more challenging and general task, where the exemplar is an arbitrary scene image that is semantically different from the given label map. We propose an end-to-end network for joint global and local feature alignment and synthesis.
  arXiv  Detail & Related papers  (2020-04-18T18:17:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.