Related papers: MagicPortrait: Temporally Consistent Face Reenactm…

Although 2D generative models have made great progress in face image generation and animation, they often suffer from undesirable artifacts such as 3D inconsistency when rendering images from different camera viewpoints. This prevents them…

Despite promising progress in face swapping task, realistic swapped images remain elusive, often marred by artifacts, particularly in scenarios involving high pose variation, color differences, and occlusion. To address these issues, we…

Recent advances in 3D face stylization have made significant strides in few to zero-shot settings. However, the degree of stylization achieved by existing methods is often not sufficient for practical applications because they are mostly…

Photo-realistic visualization and animation of expressive human faces have been a long standing challenge. 3D face modeling methods provide parametric control but generates unrealistic images, on the other hand, generative 2D models like…

Generating realistic listener facial motions in dyadic conversations remains challenging due to the high-dimensional action space and temporal dependency requirements. Existing approaches usually consider extracting 3D Morphable Model…

The recent success of pre-trained diffusion models unlocks the possibility of the automatic generation of textures for arbitrary 3D meshes in the wild. However, these models are trained in the screen space, while converting them to a…

Object-level manipulation, relocating or reorienting objects in images or videos while preserving scene realism, is central to film post-production, AR, and creative editing. Yet existing methods struggle to jointly achieve three core…

We introduce a new generative model that combines latent diffusion with persistent homology to create 3D shapes with high diversity, with a special emphasis on their topological characteristics. Our method involves representing 3D shapes as…

Pose-driven human-image animation diffusion models have shown remarkable capabilities in realistic human video synthesis. Despite the promising results achieved by previous approaches, challenges persist in achieving temporally consistent…

We address the problem of 3D inconsistency of image inpainting based on diffusion models. We propose a generative model using image pairs that belong to the same scene. To achieve the 3D-consistent and semantically coherent inpainting, we…

In recent advances of deep generative models, face reenactment -manipulating and controlling human face, including their head movement-has drawn much attention for its wide range of applicability. Despite its strong expressiveness, it is…

Creating personalized 3D animations with precise control and realistic head motions remains challenging for current speech-driven 3D facial animation methods. Editing these animations is especially complex and time consuming, requires…

We present FaceLift, a novel feed-forward approach for generalizable high-quality 360-degree 3D head reconstruction from a single image. Our pipeline first employs a multi-view latent diffusion model to generate consistent side and back…

Existing mobile devices are constrained by compact optical designs, such as small apertures, which make it difficult to produce natural, optically realistic bokeh effects. Although recent learning-based methods have shown promising results,…

Reconstructing high-quality point clouds from images remains challenging in computer vision. Existing generative-model-based approaches, particularly diffusion-model approaches that directly learn the posterior, may suffer from…

Reference-driven image completion, which restores missing regions in a target view using additional images, is particularly challenging when the target view differs significantly from the references. Existing generative methods rely solely…

Recent advances in camera-controlled video diffusion models have significantly improved video-camera alignment. However, the camera controllability still remains limited. In this work, we build upon Reward Feedback Learning and aim to…

M3DDM provides a computationally efficient framework for video outpainting via latent diffusion modeling. However, it exhibits significant quality degradation -- manifested as spatial blur and temporal inconsistency -- under challenging…

We present MagicInfinite, a novel diffusion Transformer (DiT) framework that overcomes traditional portrait animation limitations, delivering high-fidelity results across diverse character types-realistic humans, full-body figures, and…

Video face restoration aims to enhance degraded face videos into high-quality results with realistic facial details, stable identity, and temporal coherence. Recent diffusion-based methods have brought strong generative priors to…