Y Huang, H Yi, Y Xiu, T Liao, J Tang… - … Conference on 3D …, 2024 - ieeexplore.ieee.org
Despite recent research advancements in reconstructing clothed humans from a single image, accurately restoring the “unseen regions” with high-level details remains an …
N Heppert, MZ Irshad, S Zakharov… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present CARTO, a novel approach for reconstructing multiple articulated objects from a single stereo RGB observation. We use implicit object-centric representations and learn a …
We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. At the core of our model lies a neural parametric representation that …
H Zhang, S Lin, R Shao, Y Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Creating animatable avatars from static scans requires the modeling of clothing deformations in different poses. Existing learning-based methods typically add pose …
Obtaining personalized 3D animatable avatars from a monocular camera has several real world applications in gaming, virtual try-on, animation, and VR/XR, etc. However, it is very …
In this paper, we propose a novel hybrid representation and end-to-end trainable network architecture to model fully editable and customizable neural avatars. At the core of our work …
H Xue, W Xu, J Zhang, T Tang, Y Li… - Proceedings of the …, 2023 - openaccess.thecvf.com
Garments are important to humans. A visual system that can estimate and track the complete garment pose can be useful for many downstream tasks and real-world applications. In this …
Dense correspondence between humans carries powerful semantic information that can be utilized to solve fundamental problems for full-body understanding such as in-the-wild …
H Kim, H Nam, J Kim, J Park, S Lee - ACM Transactions on Graphics …, 2022 - dl.acm.org
We propose LaplacianFusion, a novel approach that reconstructs detailed and controllable 3D clothed-human body shapes from an input depth or 3D point cloud sequence. The key …