High-Resolution Complex Scene Synthesis with Transformers

• URL: http://arxiv.org/abs/2105.06458v1
• Date: Thu, 13 May 2021 17:56:07 GMT
• Title: High-Resolution Complex Scene Synthesis with Transformers
• Authors: Manuel Jahn and Robin Rombach and Bj\"orn Ommer
• Abstract summary: coarse-grained synthesis of complex scene images via deep generative models has recently gained popularity. We present an approach to this task, where the generative model is based on pure likelihood training without additional objectives. We show that the resulting system is able to synthesize high-quality images consistent with the given layouts.
• Score: 6.445605125467574
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity. However, results of current approaches still fall short of their promise of high-resolution synthesis. We hypothesize that this is mostly due to the highly engineered nature of these approaches which often rely on auxiliary losses and intermediate steps such as mask generators. In this note, we present an orthogonal approach to this task, where the generative model is based on pure likelihood training without additional objectives. To do so, we first optimize a powerful compression model with adversarial training which learns to reconstruct its inputs via a discrete latent bottleneck and thereby effectively strips the latent representation of high-frequency details such as texture. Subsequently, we train an autoregressive transformer model to learn the distribution of the discrete image representations conditioned on a tokenized version of the layouts. Our experiments show that the resulting system is able to synthesize high-quality images consistent with the given layouts. In particular, we improve the state-of-the-art FID score on COCO-Stuff and on Visual Genome by up to 19% and 53% and demonstrate the synthesis of images up to 512 x 512 px on COCO and Open Images.

Related papers

• Time Step Generating: A Universal Synthesized Deepfake Image Detector [0.4488895231267077]
  We propose a universal synthetic image detector Time Step Generating (TSG) TSG does not rely on pre-trained models' reconstructing ability, specific datasets, or sampling algorithms. We test the proposed TSG on the large-scale GenImage benchmark and it achieves significant improvements in both accuracy and generalizability.
  arXiv  Detail & Related papers  (2024-11-17T09:39:50Z)
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [62.06970466554273]
  We present Meissonic, which non-autoregressive masked image modeling (MIM) text-to-image elevates to a level comparable with state-of-the-art diffusion models like SDXL. We leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images.
  arXiv  Detail & Related papers  (2024-10-10T17:59:17Z)
• FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis [48.9652334528436]
  We introduce an innovative, training-free approach FouriScale from the perspective of frequency domain analysis. We replace the original convolutional layers in pre-trained diffusion models by incorporating a dilation technique along with a low-pass operation. Our method successfully balances the structural integrity and fidelity of generated images, achieving an astonishing capacity of arbitrary-size, high-resolution, and high-quality generation.
  arXiv  Detail & Related papers  (2024-03-19T17:59:33Z)
• StraIT: Non-autoregressive Generation with Stratified Image Transformer [63.158996766036736]
  Stratified Image Transformer(StraIT) is a pure non-autoregressive(NAR) generative model. Our experiments demonstrate that StraIT significantly improves NAR generation and out-performs existing DMs and AR methods.
  arXiv  Detail & Related papers  (2023-03-01T18:59:33Z)
• Person Image Synthesis via Denoising Diffusion Model [116.34633988927429]
  We show how denoising diffusion models can be applied for high-fidelity person image synthesis. Our results on two large-scale benchmarks and a user study demonstrate the photorealism of our proposed approach under challenging scenarios.
  arXiv  Detail & Related papers  (2022-11-22T18:59:50Z)
• DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation [56.514462874501675]
  We propose a dynamic sparse attention based Transformer model to achieve fine-level matching with favorable efficiency. The heart of our approach is a novel dynamic-attention unit, dedicated to covering the variation on the optimal number of tokens one position should focus on. Experiments on three applications, pose-guided person image generation, edge-based face synthesis, and undistorted image style transfer, demonstrate that DynaST achieves superior performance in local details.
  arXiv  Detail & Related papers  (2022-07-13T11:12:03Z)
• DiVAE: Photorealistic Images Synthesis with Denoising Diffusion Decoder [73.1010640692609]
  We propose a VQ-VAE architecture model with a diffusion decoder (DiVAE) to work as the reconstructing component in image synthesis. Our model achieves state-of-the-art results and generates more photorealistic images specifically.
  arXiv  Detail & Related papers  (2022-06-01T10:39:12Z)
• Entroformer: A Transformer-based Entropy Model for Learned Image Compression [17.51693464943102]
  We propose a novel transformer-based entropy model, termed Entroformer, to capture long-range dependencies in probability distribution estimation. The experiments show that the Entroformer achieves state-of-the-art performance on image compression while being time-efficient.
  arXiv  Detail & Related papers  (2022-02-11T08:03:31Z)
• High-Resolution Image Synthesis with Latent Diffusion Models [14.786952412297808]
  Training diffusion models on autoencoders allows for the first time to reach a near-optimal point between complexity reduction and detail preservation. Our latent diffusion models (LDMs) achieve a new state of the art for image inpainting and highly competitive performance on various tasks.
  arXiv  Detail & Related papers  (2021-12-20T18:55:25Z)
• BIGRoC: Boosting Image Generation via a Robust Classifier [27.66648389933265]
  We propose a general model-agnostic technique for improving the image quality and the distribution fidelity of generated images. Our method, termed BIGRoC, is based on a post-processing procedure via the guidance of a given robust classifier.
  arXiv  Detail & Related papers  (2021-08-08T18:05:44Z)

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.