Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China（中国教育部机器智能与先进计算重点实验室）；Microsoft Research Asia（微软亚洲研究院）；University of Tokyo（东京大学）
Yanhong Zeng, Huan Yang, Hongyang Chao, Jianbo Wang, Jianlong Fu
We present a new perspective of achieving image synthesis by viewing this task as a visual token generation problem. Different from existing paradigms that directly synthesize a full image from a single input (e.g., a latent code), the new formulation enables a flexible local manipulation for different image regions, which makes it possible to learn content-aware and fine-grained style control for image synthesis. Specifically, it takes as input a sequence of latent tokens to predict the visual tokens for synthesizing an image. Under this perspective, we propose a token-based generator (i.e.,TokenGAN). Particularly, the TokenGAN inputs two semantically different visual tokens, i.e., the learned constant content tokens and the style tokens from the latent space. Given a sequence of style tokens, the TokenGAN is able to control the image synthesis by assigning the styles to the content tokens by attention mechanism with a Transformer. We conduct extensive experiments and show that the proposed TokenGAN has achieved state-of-the-art results on several widely-used image synthesis benchmarks, including FFHQ and LSUN CHURCH with different resolutions. In particular, the generator is able to synthesize high-fidelity images with 1024x1024 size, dispensing with convolutions entirely.
Rutgers University（罗格斯大学）；Snap Inc.（Snap公司）；University of Delaware（特拉华大学）
Image and video synthesis are closely related areas aiming at generating content from noise. While rapid progress has been demonstrated in improving image-based models to handle large resolutions, high-quality renderings, and wide variations in image content, achieving comparable video generation results remains problematic. We present a framework that leverages contemporary image generators to render high-resolution videos. We frame the video synthesis problem as discovering a trajectory in the latent space of a pre-trained and fixed image generator. Not only does such a framework render high…
Automatic synthesis of faces from visual attributes is an important problem in computer vision and has wide applications in law enforcement and entertainment. With the advent of deep generative convolutional neural networks (CNNs), attempts have been made to synthesize face images from attributes and text descriptions. In this paper, we take a different approach, where we formulate the original problem as a stage-wise learning problem. We first synthesize the facial sketch corresponding to the visual attributes and then we generate the face image based on the synthesized sketch. The proposed f…
National University of Singapore（新加坡国立大学）；Tencent PCG（腾讯平台与内容事业群）
Vector-Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how the improvement in reconstruction affects the generation ability of generative transformers. In this paper, we surprisingly find that improving the reconstruction fidelity of VQ tokenizers does not necessarily improve the generation. Instead, learning to compress semantic features within VQ tokenizers significantly improves generative transformers' ability …
MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
South China University of Technology（华南理工大学）；JD Explore Academy（京东探索研究院）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）
This paper investigates the problem of pseudo-healthy synthesis that is defined as synthesizing a subject-specific pathology-free image from a pathological one. Recent approaches based on Generative Adversarial Network (GAN) have been developed for this task. However, these methods will inevitably fall into the trade-off between preserving the subject-specific identity and generating healthy-like appearances. To overcome this challenge, we propose a novel adversarial training regime, Generator versus Segmentor (GVS), to alleviate this trade-off by a divide-and-conquer strategy. We further cons…
3D-aware image synthesis aims at learning a generative model that can render photo-realistic 2D images while capturing decent underlying 3D shapes. A popular solution is to adopt the generative adversarial network (GAN) and replace the generator with a 3D renderer, where volume rendering with neural radiance field (NeRF) is commonly used. Despite the advancement of synthesis quality, existing methods fail to obtain moderate 3D shapes. We argue that, considering the two-player game in the formulation of GANs, only making the generator 3D-aware is not enough. In other words, displacing the gener…
Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Shanghai Innovation Institute（上海创新研究院）；Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究院）；Department of Computer Science, The University of Hong Kong（香港大学计算机科学系）
Generative adversarial networks (GANs) have enabled photorealistic image synthesis and editing. However, due to the high computational cost of large-scale generators (e.g., StyleGAN2), it usually takes seconds to see the results of a single edit on edge devices, prohibiting interactive user experience. In this paper, we take inspirations from modern rendering software and propose Anycost GAN for interactive natural image editing. We train the Anycost GAN to support elastic resolutions and channels for faster image generation at versatile speeds. Running subsets of the full generator produce ou…
We propose a novel hierarchical approach for text-to-image synthesis by inferring semantic layout. Instead of learning a direct mapping from text to image, our algorithm decomposes the generation process into multiple steps, in which it first constructs a semantic layout from the text by the layout generator and converts the layout to an image by the image generator. The proposed layout generator progressively constructs a semantic layout in a coarse-to-fine manner by generating object bounding boxes and refining each box by estimating object shapes inside the box. The image generator synthesi…
In this work, we propose and validate a framework to leverage language-image pretraining representations for training-free zero-shot sketch-to-image synthesis. We show that disentangled content and style representations can be utilized to guide image generators to employ them as sketch-to-image generators without (re-)training any parameters. Our approach for disentangling style and content entails a simple method consisting of elementary arithmetic assuming compositionality of information in representations of input sketches. Our results demonstrate that this approach is competitive with stat…
The style-based GAN (StyleGAN) architecture achieved state-of-the-art results for generating high-quality images, but it lacks explicit and precise control over camera poses. The recently proposed NeRF-based GANs made great progress towards 3D-aware generators, but they are unable to generate high-quality images yet. This paper presents CIPS-3D, a style-based, 3D-aware generator that is composed of a shallow NeRF network and a deep implicit neural representation (INR) network. The generator synthesizes each pixel value independently without any spatial convolution or upsampling operation. In a…
AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis
Institute of Advanced Medicine and Frontier Technology（先进医学与前沿技术研究院）；Hefei University of Technology（合肥工业大学）；Key Laboratory of Knowledge Engineering With Big Data, Ministry of Education（大数据知识工程重点实验室）；Department of Automation, Tsinghua University（清华大学自动化系）
Existing methods for 3D-aware image synthesis largely depend on the 3D pose distribution pre-estimated on the training set. An inaccurate estimation may mislead the model into learning faulty geometry. This work proposes PoF3D that frees generative radiance fields from the requirements of 3D pose priors. We first equip the generator with an efficient pose learner, which is able to infer a pose from a latent code, to approximate the underlying true pose distribution automatically. We then assign the discriminator a task to learn pose distribution under the supervision of the generator and to di…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Qihoo 360 Artificial Intelligence Institute（奇虎360人工智能研究院）；University of Chinese Academy of Sciences（中国科学院大学）；National University of Singapore（新加坡国立大学）
Style synthesis attracts great interests recently, while few works focus on its dual problem "style separation". In this paper, we propose the Style Separation and Synthesis Generative Adversarial Network (S3-GAN) to simultaneously implement style separation and style synthesis on object photographs of specific categories. Based on the assumption that the object photographs lie on a manifold, and the contents and styles are independent, we employ S3-GAN to build mappings between the manifold and a latent vector space for separating and synthesizing the contents and styles. The S3-GAN consists …
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）；Yandex；University of Oxford（牛津大学）
The recent work of Gatys et al., who characterized the style of an image by the statistics of convolutional neural network filters, ignited a renewed interest in the texture generation and image stylization problems. While their image generation technique uses a slow optimization process, recently several authors have proposed to learn generator neural networks that can produce similar outputs in one quick forward pass. While generator networks are promising, they are still inferior in visual quality and diversity compared to generation-by-optimization. In this work, we advance them in two sig…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Adobe Research（奥多比研究院）
We propose a new approach for high resolution semantic image synthesis. It consists of one base image generator and multiple class-specific generators. The base generator generates high quality images based on a segmentation map. To further improve the quality of different objects, we create a bank of Generative Adversarial Networks (GANs) by separately training class-specific models. This has several benefits including -- dedicated weights for each class; centrally aligned data for each model; additional training data from other sources, potential of higher resolution and quality; and easy ma…
Huazhong University of Science and Technology（华中科技大学）；Peking University（北京大学）
In this paper, we focus on semantically multi-modal image synthesis (SMIS) task, namely, generating multi-modal images at the semantic level. Previous work seeks to use multiple class-specific generators, constraining its usage in datasets with a small number of classes. We instead propose a novel Group Decreasing Network (GroupDNet) that leverages group convolutions in the generator and progressively decreases the group numbers of the convolutions in the decoder. Consequently, GroupDNet is armed with much more controllability on translating semantic labels to natural images and has plausible …
Training a text-to-image generator in the general domain (e.g., Dall.e, CogView) requires huge amounts of paired text-image data, which is too expensive to collect. In this paper, we propose a self-supervised scheme named as CLIP-GEN for general text-to-image generation with the language-image priors extracted with a pre-trained CLIP model. In our approach, we only require a set of unlabeled images in the general domain to train a text-to-image generator. Specifically, given an image without text labels, we first extract the embedding of the image in the united language-vision embedding space …
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
Tsinghua University（清华大学）；Westlake University（西湖大学）；Zhejiang University（浙江大学）；Hong Kong University of Science and Technology（香港科学与技术大学）；OPPO；Shanghai AI Lab（上海人工智能实验室）
Computationally synthesized blood vessels can be used for training and evaluation of medical image analysis applications. We propose a deep generative model to synthesize blood vessel geometries, with an application to coronary arteries in cardiac CT angiography (CCTA). In the proposed method, a Wasserstein generative adversarial network (GAN) consisting of a generator and a discriminator network is trained. While the generator tries to synthesize realistic blood vessel geometries, the discriminator tries to distinguish synthesized geometries from those of real blood vessels. Both real and syn…
FeaTok: Feature-Loss Tokenization for Image Generation
Mila - Québec AI Institute（Mila - 魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；FAIR at Meta（Meta FAIR研究院）；Columbia University（哥伦比亚大学）；University of Oxford（牛津大学）；McGill University（麦吉尔大学）
Hierarchical and Step-Layer-Wise Tuning of Attention Specialty for Multi-Instance Synthesis in Diffusion Transformers
School of Systems and Computing University of New South Wales（系统与计算学院 新南威尔士大学）；School of Engineering Australian National University（工程学院 澳大利亚国立大学）；School of Business University of New South Wales（商学院 新南威尔士大学）；Australian Institute for Machine Learning University of Adelaide（机器学习研究所 阿德莱德大学）；School of Computer Science and Engineering University of New South Wales（计算机科学与工程学院 新南威尔士大学）；School of Computer Science University of Technology Sydney（计算机科学学院 技术大学悉尼）
Understanding three-dimensional (3D) geometries from two-dimensional (2D) images without any labeled information is promising for understanding the real world without incurring annotation cost. We herein propose a novel generative model, RGBD-GAN, which achieves unsupervised 3D representation learning from 2D images. The proposed method enables camera parameter-conditional image generation and depth image generation without any 3D annotations, such as camera poses or depth. We use an explicit 3D consistency loss for two RGBD images generated from different camera parameters, in addition to the…
VolDiT: Controllable Volumetric Medical Image Synthesis with Diffusion Transformers
Institute for Artificial Intelligence in Cardiovascular Medicine, Medical Faculty of Heidelberg University, Heidelberg University（海德堡大学医学院心血管医学人工智能研究所）；Department of Cardiology, Angiology, Pneumology, Heidelberg University Hospital（海德堡大学医院心脏病学、血管学、肺病学系）；DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim（德国心血管研究中心（DZHK）海德堡/曼海姆合作站点）；University Medical Center of the Johannes Gutenberg-University Mainz（美因茨约翰内斯·古腾堡大学医学中心）
Tsinghua University（清华大学）；University of Science and Technology Beijing（北京科技大学）
Video generation has achieved rapid progress benefiting from high-quality renderings provided by powerful image generators. We regard the video synthesis task as generating a sequence of images sharing the same contents but varying in motions. However, most previous video synthesis frameworks based on pre-trained image generators treat content and motion generation separately, leading to unrealistic generated videos. Therefore, we design a novel framework to build the motion space, aiming to achieve content consistency and fast convergence for video generation. We present MotionVideoGAN, a nov…
This paper presents a novel method to deal with the challenging task of generating photographic images conditioned on semantic image descriptions. Our method introduces accompanying hierarchical-nested adversarial objectives inside the network hierarchies, which regularize mid-level representations and assist generator training to capture the complex image statistics. We present an extensile single-stream generator architecture to better adapt the jointed discriminators and push generated images up to high resolutions. We adopt a multi-purpose adversarial loss to encourage more effective image…
Facebook AI；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；The University of Hong Kong（香港大学）
We propose StyleNeRF, a 3D-aware generative model for photo-realistic high-resolution image synthesis with high multi-view consistency, which can be trained on unstructured 2D images. Existing approaches either cannot synthesize high-resolution images with fine details or yield noticeable 3D-inconsistent artifacts. In addition, many of them lack control over style attributes and explicit 3D camera poses. StyleNeRF integrates the neural radiance field (NeRF) into a style-based generator to tackle the aforementioned challenges, i.e., improving rendering efficiency and 3D consistency for high-res…
Duke University（杜克大学）；Duke University School of Medicine（杜克大学医学院）
Recent advancements in conditional Generative Adversarial Networks (cGANs) have shown promises in label guided image synthesis. Semantic masks, such as sketches and label maps, are another intuitive and effective form of guidance in image synthesis. Directly incorporating the semantic masks as constraints dramatically reduces the variability and quality of the synthesized results. We observe this is caused by the incompatibility of features from different inputs (such as mask image and latent vector) of the generator. To use semantic masks as guidance whilst providing realistic synthesized res…
Technion - Israel Institute of Technology（以色列理工学院）
The interest of the deep learning community in image synthesis has grown massively in recent years. Nowadays, deep generative methods, and especially Generative Adversarial Networks (GANs), are leading to state-of-the-art performance, capable of synthesizing images that appear realistic. While the efforts for improving the quality of the generated images are extensive, most attempts still consider the generator part as an uncorroborated "black-box". In this paper, we aim to provide a better understanding and design of the image generation process. We interpret existing generators as implicitly…
