Related papers: DyPE: Dynamic Position Extrapolation for Ultra Hig…
Recently most successful image synthesis models are multi stage process to combine the advantages of different methods, which always includes a VAE-like model for faithfully reconstructing embedding to image and a prior model to generate…
Ultra-high-resolution image synthesis holds significant potential, yet remains an underexplored challenge due to the absence of standardized benchmarks and computational constraints. In this paper, we establish Aesthetic-4K, a meticulously…
Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of an image according to the provided text description. %…
Transformers have recently been shown to generate high quality images from text input. However, the existing method of pose conditioning using skeleton image tokens is computationally inefficient and generate low quality images. Therefore…
Text-to-image diffusion models (DMs) inadvertently reproduce copyrighted styles and protected visual concepts, raising legal and ethical concerns. Concept erasure has emerged as a safeguard, aiming to selectively suppress such concepts…
We propose a unified diffusion model-based correction and super-resolution method to enhance the fidelity and resolution of diverse low-quality data through a two-step pipeline. First, the correction step employs a novel enhanced stochastic…
Generating high-quality labeled image datasets is crucial for training accurate and robust machine learning models in the field of computer vision. However, the process of manually labeling real images is often time-consuming and costly. To…
Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…
We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustness. Applying DiffAug to a given example consists of one…
Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements…
Recent advancement in text-to-image models (e.g., Stable Diffusion) and corresponding personalized technologies (e.g., DreamBooth and LoRA) enables individuals to generate high-quality and imaginative images. However, they often suffer from…
Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers…
Coherent diffraction imaging is a high-resolution imaging technique whose potential can be greatly enhanced by applying the extrapolation method presented here. We demonstrate enhancement in resolution of a non-periodical object…
Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. Unlike existing methods that directly insert objects into the background, adaptive and interactive fusion…
Image retouching aims to enhance the visual quality of photos. Considering the different aesthetic preferences of users, the target of retouching is subjective. However, current retouching methods mostly adopt deterministic models, which…
Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…
We aim to leverage diffusion to address the challenging image matting task. However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles…
Generating high-quality 3D assets from text and images has long been challenging, primarily due to the absence of scalable 3D representations capable of capturing intricate geometry distributions. In this work, we introduce Direct3D, a…
Autoregressive video diffusion models have emerged as a scalable paradigm for long video generation. However, they often suffer from severe extrapolation failure, where rapid error accumulation leads to significant temporal degradation when…
Transformer-based methods have swept the benchmarks on 2D and 3D detection on images. Because tokenization before the attention mechanism drops the spatial information, positional encoding becomes critical for those methods. Recent works…