InfinityGAN: Towards Infinite-Pixel Image Synthesis
We present a novel framework, InfinityGAN, for arbitrary-sized image generation. The task is associated with several key challenges. First, scaling existing models to an arbitrarily large image size is resource-constrained, in terms of both computation and availability of large-field-of-view training data. InfinityGAN trains and infers in a seamless patch-by-patch manner with low computational resources. Second, large images should be locally and globally consistent, avoid repetitive patterns, and look realistic. To address these, InfinityGAN disentangles global appearances, local structures, and textures. With this formulation, we can generate images with spatial size and level of details not attainable before. Experimental evaluation validates that InfinityGAN generates images with superior realism compared to baselines and features parallelizable inference. Finally, we show several applications unlocked by our approach, such as spatial style fusion, multi-modal outpainting, and image inbetweening. All applications can be operated with arbitrary input and output sizes. Please find the full version of the paper at https://openreview.net/forum?id=ufGMqIM0a4b .
Code (1)
Tasks
Image GenerationScene GenerationSimilar Papers 제목 키워드 기반
InfiniCity: Infinite-Scale City Synthesis
Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noises. InfiniCity decomposes the seemingly…
Image GenerationNeural Rendering$\infty$-Brush: Controllable Large Image Synthesis with Diffusion Models in Infinite Dimensions
Synthesizing high-resolution images from intricate, domain-specific information remains a significant challenge in generative modeling, particularly for applications in large-image domains such as digital histopathology …
Computational EfficiencyImage GenerationPixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation. However, existing methods still suffer from excessive memory footprint and computat…
Image GenerationregressionUltra-High-Definition Dynamic Multi-Exposure Image Fusion via Infinite Pixel Learning
With the continuous improvement of device imaging resolution, the popularity of Ultra-High-Definition (UHD) images is increasing. Unfortunately, existing methods for fusing multi-exposure images in dynamic scenes are des…
GPULarge Language ModelMulti-Exposure Image FusionInfinite Texture: Text-guided High Resolution Diffusion Texture Synthesis
We present Infinite Texture, a method for generating arbitrarily large texture images from a text prompt. Our approach fine-tunes a diffusion model on a single texture, and learns to embed that statistical distribution i…
GPUTexture Synthesis