Related papers: A Pytorch Reproduction of Masked Generative Image …
This study introduces a Masked Degradation Classification Pre-Training method (MaskDCPT), designed to facilitate the classification of degradation types in input images, leading to comprehensive image restoration pre-training. Unlike…
Non-autoregressive generative transformers recently demonstrated impressive image generation performance, and orders of magnitude faster sampling than their autoregressive counterparts. However, optimal parallel sampling from the true joint…
Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…
Small CNN-based models usually require transferring knowledge from a large model before they are deployed in computationally resource-limited edge devices. Masked image modeling (MIM) methods achieve great success in various visual tasks…
Despite remarkable progress in image translation, the complex scene with multiple discrepant objects remains a challenging problem. The translated images have low fidelity and tiny objects in fewer details causing unsatisfactory performance…
We offer a method for one-shot mask-guided image synthesis that allows controlling manipulations of a single image by inverting a quasi-robust classifier equipped with strong regularizers. Our proposed method, entitled MAGIC, leverages…
Vision transformers have shown unprecedented levels of performance in tackling various visual perception tasks in recent years. However, the architectural and computational complexity of such network architectures have made them challenging…
Diffusion Transformer (DiT) has driven significant progress in image generation tasks. However, DiT inferencing is notoriously compute-intensive and incurs long latency even on datacenter-scale GPUs, primarily due to its iterative nature…
The majority of the recent iterative approaches in 4DCT not only rely on nested iterations, thereby increasing computational complexity and constraining potential acceleration, but also fail to provide a theoretical proof of convergence for…
We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency. Due to the tokenizers' limitations, prior masked AR models…
Photorealistic style transfer aims to transfer the style of one image to another, but preserves the original structure and detail outline of the content image, which makes the content image still look like a real shot after the style…
Applications that involve supervised training require paired images. Researchers of single image super-resolution (SISR) create such images by artificially generating blurry input images from the corresponding ground truth. Similarly we can…
This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let…
We introduce native-resolution image synthesis, a novel generative modeling paradigm that enables the synthesis of images at arbitrary resolutions and aspect ratios. This approach overcomes the limitations of conventional fixed-resolution,…
In this paper, we study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods, e.g., GANs and diffusion models. Cutting-edge solutions start to explore the benefits of…
State-of-the-art models for high-resolution image generation, such as BigGAN and VQVAE-2, require an incredible amount of compute resources and/or time (512 TPU-v3 cores) to train, putting them out of reach for the larger research…
Generating images with both photorealism and multiview 3D consistency is crucial for 3D-aware GANs, yet existing methods struggle to achieve them simultaneously. Improving the photorealism via CNN-based 2D super-resolution can break the…
Single Image Super-resolution (SISR) produces high-resolution images with fine spatial resolutions from aremotely sensed image with low spatial resolution. Recently, deep learning and generative adversarial networks(GANs) have made…
Masked image modeling has demonstrated great potential to eliminate the label-hungry problem of training large-scale vision Transformers, achieving impressive performance on various downstream tasks. In this work, we propose a unified view…
We present FlashLips, a two-stage, mask-free lip-sync system that decouples lips control from rendering and achieves real-time performance, with our U-Net variant running at over 100 FPS on a single GPU, while matching the visual quality of…