Rendering photorealistic and dynamically moving human heads is crucial for ensuring a pleasant and immersive experience in AR/VR and video conferencing applications …
In this paper, we propose a novel framework, Tracking-free Relightable Avatar (TRAvatar), for capturing and reconstructing high-fidelity 3D avatars. Compared to previous methods …
Y Han, J Lyu, F Xu - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Facial geometry and appearance capture have demonstrated tremendous success in 3D scanning real humans in studios. Recent works propose to democratize this technique while …
J Kong, B Xu, X Song, C Qian, J Luo, Y He - arXiv preprint arXiv …, 2023 - arxiv.org
Neural radiance fields (NeRF) typically require a complete set of images taken from multiple camera perspectives to accurately reconstruct geometric details. However, this approach …
While recent works have achieved great success on one-shot 3D common object generation, high quality and fidelity 3D head generation from a single image remains a great …
D Jin, J Hu, B Xu, Y Dai, C Qian, Y He - arXiv preprint arXiv:2312.06085, 2023 - arxiv.org
This paper presents a novel two-stage approach for reconstructing human faces from sparse- view images, a task made challenging by the unique geometry and complex skin reflectance …
In high-end visual effects pipelines, a customized (and expensive) light stage system is (typically) used to scan an actor in order to acquire both geometry and texture for various …
We adopt MetaShape 1 to calibrate a shared camera intrinsic matrix for all the recorded frames and a camera extrinsic matrix for each frame. We translate and scale the mesh …