no code implementations • 13 Dec 2024 • Tuur Stuyck, Gene Wei-Chin Lin, Egor Larionov, Hsiao-yu Chen, Aljaz Bozic, Nikolaos Sarafianos, Doug Roble
Realistic hair motion is crucial for high-quality avatars, but it is often limited by the computational resources available for real-time applications.
no code implementations • 11 Dec 2024 • Will Gao, Dilin Wang, Yuchen Fan, Aljaz Bozic, Tuur Stuyck, Zhengqin Li, Zhao Dong, Rakesh Ranjan, Nikolaos Sarafianos
We formulate shape editing as a conditional reconstruction problem, where the model must reconstruct the input shape with the exception of a specified 3D region, in which the geometry should be generated from the conditional signal.
no code implementations • 24 May 2024 • Jorge Condor, Sebastien Speierer, Lukas Bode, Aljaz Bozic, Simon Green, Piotr Didyk, Adrian Jarabo
We demonstrate our method as a compact and efficient alternative to other forms of volume modeling for forward and inverse rendering of scattering media.
no code implementations • CVPR 2024 • Michael Fischer, Zhengqin Li, Thu Nguyen-Phuoc, Aljaz Bozic, Zhao Dong, Carl Marshall, Tobias Ritschel
A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and appearance of a scene.
no code implementations • 14 Dec 2023 • Ziyan Wang, Giljoo Nam, Aljaz Bozic, Chen Cao, Jason Saragih, Michael Zollhoefer, Jessica Hodgins
In this paper, we present a novel method for creating high-fidelity avatars with diverse hairstyles.
no code implementations • 16 Aug 2023 • Edith Tretschk, Vladislav Golyanik, Michael Zollhoefer, Aljaz Bozic, Christoph Lassner, Christian Theobalt
We propose SceNeRFlow to reconstruct a general, non-rigid scene in a time-consistent manner.
no code implementations • 15 Jun 2023 • Shizhan Zhu, Shunsuke Saito, Aljaz Bozic, Carlos Aliaga, Trevor Darrell, Christop Lassner
Reconstructing and relighting objects and scenes under varying lighting conditions is challenging: existing neural rendering methods often cannot handle the complex interactions between materials and light.
1 code implementation • CVPR 2020 • Aljaz Bozic, Michael Zollhofer, Christian Theobalt, Matthias Niessner
Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus.