Related papers: ExpertGen: Training-Free Expert Guidance for Contr…
Zero-shot, training-free, image-based text-to-video generation is an emerging area that aims to generate videos using existing image-based diffusion models. Current methods in this space require specific architectural changes to image…
Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output remains a fundamental challenge. Identity consistency is crucial for downstream…
Large-scale generative models have achieved remarkable advancements in various visual tasks, yet their application to shadow removal in images remains challenging. These models often generate diverse, realistic details without adequate…
Recent text-to-image diffusion models are able to generate convincing results of unprecedented quality. However, it is nearly impossible to control the shapes of different regions/objects or their layout in a fine-grained fashion. Previous…
Face animation has achieved much progress in computer vision. However, prevailing GAN-based methods suffer from unnatural distortions and artifacts due to sophisticated motion deformation. In this paper, we propose a Face Animation…
Facial expression editing is a challenging task as it needs a high-level semantic understanding of the input face image. In conventional methods, either paired training data is required or the synthetic face resolution is low. Moreover,…
Research in vision-language models has seen rapid developments off-late, enabling natural language-based interfaces for image generation and manipulation. Many existing text guided manipulation techniques are restricted to specific classes…
Talking face generation has historically struggled to produce head movements and natural facial expressions without guidance from additional reference videos. Recent developments in diffusion-based generative models allow for more realistic…
The existing text-guided image synthesis methods can only produce limited quality results with at most \mbox{$\text{256}^2$} resolution and the textual instructions are constrained in a small Corpus. In this work, we propose a unified…
The utilization of synthetic data for fingerprint recognition has garnered increased attention due to its potential to alleviate privacy concerns surrounding sensitive biometric data. However, current methods for generating fingerprints…
Enabling image generation models to be spatially controlled is an important area of research, empowering users to better generate images according to their own fine-grained specifications via e.g. edge maps, poses. Although this task has…
Long video generation remains a challenging and compelling topic in computer vision. Diffusion based models, among the various approaches to video generation, have achieved state of the art quality with their iterative denoising procedures.…
Self-supervised representation learning has gained increasing attention for strong generalization ability without relying on paired datasets. However, it has not been explored sufficiently for facial representation. Self-supervised facial…
ControlNet offers a powerful way to guide diffusion-based generative models, yet most implementations rely on ad-hoc heuristics to choose which network blocks to control-an approach that varies unpredictably with different tasks. To address…
In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending. In specific, in the training…
The rapid advancement in image generation models has predominantly been driven by diffusion models, which have demonstrated unparalleled success in generating high-fidelity, diverse images from textual prompts. Despite their success,…
Facial images have extensive practical applications. Although the current large-scale text-image diffusion models exhibit strong generation capabilities, it is challenging to generate the desired facial images using only text prompt. Image…
Accurate and controllable image editing is a challenging task that has attracted significant attention recently. Notably, DragGAN is an interactive point-based image editing framework that achieves impressive editing results with…
Diverse human motion generation is an increasingly important task, having various applications in computer vision, human-computer interaction and animation. While text-to-motion synthesis using diffusion models has shown success in…
In this work, we present RadGazeGen, a novel framework for integrating experts' eye gaze patterns and radiomic feature maps as controls to text-to-image diffusion models for high fidelity medical image generation. Despite the recent success…