no code implementations • 15 Mar 2024 • Peter Kocsis, Julien Philip, Kalyan Sunkavalli, Matthias Nießner, Yannick Hold-Geoffroy
Our method is the first that enables the generation of images with controllable, consistent lighting and performs on par with specialized relighting state-of-the-art methods.
1 code implementation • 19 Dec 2023 • Peter Kocsis, Vincent Sitzmann, Matthias Nießner
We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes.
no code implementations • 11 Oct 2022 • Peter Kocsis, Peter Súkeník, Guillem Brasó, Matthias Nießner, Laura Leal-Taixé, Ismail Elezi
This allows us to improve the generalization of a CNN-based model without any increase in the number of weights at test time.