no code implementations • 22 Apr 2022 • Verica Lazova, Vladimir Guzov, Kyle Olszewski, Sergey Tulyakov, Gerard Pons-Moll
With the aim of obtaining interpretable and controllable scene representations, our model couples learnt scene-specific feature volumes with a scene agnostic neural rendering network.
1 code implementation • CVPR 2021 • Julian Chibane, Aayush Bansal, Verica Lazova, Gerard Pons-Moll
Recent neural view synthesis methods have achieved impressive quality and realism, surpassing classical pipelines which rely on multi-view reconstruction.
no code implementations • 20 Aug 2019 • Verica Lazova, Eldar Insafutdinov, Gerard Pons-Moll
In order to learn our model in a common UV-space, we non-rigidly register the SMPL model to thousands of 3D scans, effectively encoding textures and geometries as images in correspondence.