Related papers: Training-Free Style Consistent Image Synthesis wit…

We introduce a data-driven approach for interactively synthesizing in-the-wild images from semantic label maps. Our approach is dramatically different from recent work in this space, in that we make use of no learning. Instead, our approach…

The deep learning revolution has strongly impacted low-level image processing tasks such as style/domain transfer, enhancement/restoration, and visual quality assessments. Despite often being treated separately, the aforementioned tasks…

Diffusionmodels(DMs)havedemonstratedremarkableachievements in synthesizing images of high fidelity and diversity. However, the extensive computational requirements and slow generative speed of diffusion models have limited their widespread…

Controllable image generation has always been one of the core demands in image generation, aiming to create images that are both creative and logical while satisfying additional specified conditions. In the post-AIGC era, controllable…

Previous text-to-image synthesis algorithms typically use explicit textual instructions to generate/manipulate images accurately, but they have difficulty adapting to guidance in the form of coarsely matched texts. In this work, we attempt…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains due to their creative and high-fidelity image generation. Nonetheless, existing large-scale diffusion models…

Perceptual quality assessment of user generated content (UGC) videos is challenging due to the requirement of large scale human annotated videos for training. In this work, we address this challenge by first designing a self-supervised…

Content-Preserving Style transfer, given content and style references, remains challenging for Diffusion Transformers (DiTs) due to its internal entangled content and style features. In this technical report, we propose the first…

Despite the advancements in diffusion-based image style transfer, existing methods are commonly limited by 1) semantic gap: the style reference could miss proper content semantics, causing uncontrollable stylization; 2) reliance on extra…

In this paper, we propose a novel virtual try-on from unconstrained designs (ucVTON) task to enable photorealistic synthesis of personalized composite clothing on input human images. Unlike prior arts constrained by specific input types,…

Text-guided image editing is an essential task that enables users to modify images through natural language descriptions. Recent advances in diffusion models and rectified flows have significantly improved editing quality, primarily relying…

What defines a visual style? Fashion styles emerge organically from how people assemble outfits of clothing, making them difficult to pin down with a computational model. Low-level visual similarity can be too specific to detect…

We investigate cross-quality knowledge distillation (CQKD), a knowledge distillation method where knowledge from a teacher network trained with full-resolution images is transferred to a student network that takes as input low-resolution…

Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to do this well. To address this problem, previous works have proposed automatic retouching systems based on supervised…

Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods struggle to address the trade-off in shared latent space for…

Under limited data setting, GANs often struggle to navigate and effectively exploit the input latent space. Consequently, images generated from adjacent variables in a sparse input latent space may exhibit significant discrepancies in…

State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…

Quality assessment and aesthetics assessment aim to evaluate the perceived quality and aesthetics of visual content. Current learning-based methods suffer greatly from the scarcity of labeled data and usually perform sub-optimally in terms…

We propose a new strategy to improve the accuracy and robustness of image classification. First, we train a baseline CNN model. Then, we identify challenging regions in the feature space by identifying all misclassified samples, and…