Related papers: MoCha:End-to-End Video Character Replacement witho…
Marker-based motion capture (MoCap) systems have long been the gold standard for accurate 4D human modeling, yet their reliance on specialized hardware and markers limits scalability and real-world deployment. Advancing reliable markerless…
3D human motion capture from monocular RGB images respecting interactions of a subject with complex and possibly deformable environments is a very challenging, ill-posed and under-explored problem. Existing methods address it only weakly…
Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on…
Audio-driven human animation models often suffer from identity drift during temporal autoregressive generation, where characters gradually lose their identity over time. One solution is to generate keyframes as intermediate temporal anchors…
Masked autoencoders (MAEs) have emerged recently as art self-supervised spatiotemporal representation learners. Inheriting from the image counterparts, however, existing video MAEs still focus largely on static appearance learning whilst…
Muscle-based systems have the potential to provide both anatomical accuracy and semantic interpretability as compared to blendshape models; however, a lack of expressivity and differentiability has limited their impact. Thus, we propose…
Synthesizing human--object interaction (HOI) videos has broad practical value in e-commerce, digital advertising, and virtual marketing. However, current diffusion models, despite their photorealistic rendering capability, still frequently…
We propose an image-based, facial reenactment system that replaces the face of an actor in an existing target video with the face of a user from a source video, while preserving the original target performance. Our system is fully automatic…
Recent advancements in personalized Text-to-Video (T2V) generation have made significant strides in synthesizing character-specific content. However, these methods face a critical limitation: the inability to perform fine-grained control…
Creating realistic 3D facial animation is crucial for various applications in the movie production and gaming industry, especially with the burgeoning demand in the metaverse. However, prevalent methods such as blendshape-based approaches…
Text-motion retrieval systems learn shared embedding spaces from motion-caption pairs via contrastive objectives. However, each caption is not a deterministic label but a sample from a distribution of valid descriptions: different…
Video personalization, which generates customized videos using reference images, has gained significant attention. However, prior methods typically focus on single-concept personalization, limiting broader applications that require…
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics…
Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…
Learning an animatable and clothed human avatar model with vivid dynamics and photorealistic appearance from multi-view videos is an important foundational research problem in computer graphics and vision. Fueled by recent advances in…
We propose ClipFace, a novel self-supervised approach for text-guided editing of textured 3D morphable model of faces. Specifically, we employ user-friendly language prompts to enable control of the expressions as well as appearance of 3D…
Instruction tuning of Large Vision-language Models (LVLMs) has revolutionized the development of versatile models with zero-shot generalization across a wide range of downstream vision-language tasks. However, the diversity of training…
We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Despite the significant progress recently on this topic, with several methods exploring shared canonical neural…
This paper studies the task of full generative modelling of realistic images of humans, guided only by coarse sketch of the pose, while providing control over the specific instance or type of outfit worn by the user. This is a difficult…
Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial…