no code implementations • 7 Feb 2024 • Xingchang Huang, Corentin Salaün, Cristina Vasconcelos, Christian Theobalt, Cengiz Öztireli, Gurprit Singh
In this paper, we introduce a novel and general class of diffusion models taking correlated noise within and across images into account.
no code implementations • 24 Nov 2023 • Corentin Salaün, Xingchang Huang, Iliyan Georgiev, Niloy J. Mitra, Gurprit Singh
Nevertheless, existing algorithms have struggled to efficiently integrate importance sampling into machine learning frameworks.
no code implementations • 27 Sep 2023 • Martin Balint, Karol Myszkowski, Hans-Peter Seidel, Gurprit Singh
By combining proportional and finite-difference samples, we continuously reduce the variance of our novel gradient meta-estimators throughout the optimisation process.
no code implementations • NeurIPS 2021 • Quan Zheng, Gurprit Singh, Hans-Peter Seidel
We propose to learn neural representations for participating media with a complete simulation of global illumination.
no code implementations • 4 Dec 2020 • Vassillen Chizhov, Iliyan Georgiev, Karol Myszkowski, Gurprit Singh
To find solutions, we present a set of algorithms that provide varying trade-offs between quality and speed, showing substantial improvements over prior state of the art.
Image Generation Graphics I.3.7
no code implementations • ECCV 2020 • Yifan Xu, Tianqi Fan, Yi Yuan, Gurprit Singh
Deep implicit field regression methods are effective for 3D reconstruction from single-view images.