Related papers: SyncHuman: Synchronizing 2D and 3D Generative Mode…
The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant…
Recovering textured 3D models of non-rigid human body shapes is challenging due to self-occlusions caused by complex body poses and shapes, clothing obstructions, lack of surface texture, background clutter, sparse set of cameras with…
Human video synthesis aims to create lifelike characters in various environments, with wide applications in VR, storytelling, and content creation. While 2D diffusion-based methods have made significant progress, they struggle to generalize…
Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency.…
We describe the first method to automatically estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image. We estimate a full 3D mesh and show that 2D joints alone carry a surprising amount of…
Dynamic multi-person mesh recovery has broad applications in sports broadcasting, virtual reality, and video games. However, current multi-view frameworks rely on a time-consuming camera calibration procedure. In this work, we focus on…
Generating talking avatar driven by audio remains a significant challenge. Existing methods typically require high computational costs and often lack sufficient facial detail and realism, making them unsuitable for applications that demand…
Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. To this end, we propose the task of joint 3D human semantic segmentation, instance segmentation and…
Reconstructing 3D humans from images captured at multiple perspectives typically requires pre-calibration, like using checkerboards or MVS algorithms, which limits scalability and applicability in diverse real-world scenarios. In this work,…
3D vision systems are fundamentally constrained by their reliance on visual overlap: reconstruction methods require it for geometric alignment, while generative models use it to enforce multi-view consistency. This limitation is…
Pose stylization, which aims to synthesize stylized content aligning with target poses, serves as a fundamental task across 2D, 3D, and video domains. In the 3D realm, prevailing approaches typically rely on a cascade pipeline: first…
Robust 3D human pose estimation is crucial to ensure safe and effective human-robot collaboration. Accurate human perception,however, is particularly challenging in these scenarios due to strong occlusions and limited camera viewpoints.…
We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions and tracks human bodies even when they go outside the camera's field of…
Generative models have gained significant attention in novel view synthesis (NVS) by alleviating the reliance on dense multi-view captures. However, existing methods typically fall into a conventional paradigm, where generative models first…
We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views while preserving specific details of the input image. High-fidelity 3D GAN inversion is inherently…
High-quality, animatable 3D human avatar reconstruction from monocular videos offers significant potential for reducing reliance on complex hardware, making it highly practical for applications in game development, augmented reality, and…
We introduce PeeledHuman - a novel shape representation of the human body that is robust to self-occlusions. PeeledHuman encodes the human body as a set of Peeled Depth and RGB maps in 2D, obtained by performing ray-tracing on the 3D body…
Recent diffusion methods have made significant progress in generating videos from single images due to their powerful visual generation capabilities. However, challenges persist in image-to-video synthesis, particularly in human video…
Recent works on dynamic 3D neural field reconstruction assume the input from synchronized multi-view videos whose poses are known. The input constraints are often not satisfied in real-world setups, making the approach impractical. We show…
In this paper, we revisit the problem of 3D human modeling from two orthogonal silhouettes of individuals (i.e., front and side views). Different from our prior work, a supervised learning approach based on convolutional neural network…