by Martina Megaro | Apr 25, 2022 | Capture, Digital Humans, Machine Learning
Shape Transformers: Topology-Independent 3D Shape Models Using Transformers We present a new nonlinear parametric 3D shape model based on transformer architectures. April 25, 2022Eurographics 2022 Authors Prashanth Chandran (DisneyResearch|Studios/ETH Joint...
by Martina Megaro | Apr 25, 2022 | Capture, Digital Humans, Machine Learning
Improved Lighting Models for Facial Appearance Capture We compare the results obtained with a state-of-the-art appearance capture method [RGB∗20], with and without our proposed improvements to the lighting model. April 25, 2022Eurographics 2022 Authors...
by Martina Megaro | Nov 30, 2021 | Capture, Digital Humans, Machine Learning
Rendering with Style: Combining Traditional and Neural Approaches for High-Quality Face Rendering We propose to combine incomplete, high-quality renderings showing only facial skin with recent methods for neural rendering of faces, in order to automatically and...
by Martina Megaro | Jul 30, 2021 | Rendering, Visual Computing
Deep Compositional Denoising for High-quality Monte Carlo Rendering We propose a deep-learning method for automatically decomposing noisy Monte Carlo renderings into components that kernel-predicting denoisers can denoise more effectively. June 29, 2021Eurographics...
by Martina Megaro | Jun 19, 2021 | Capture, Digital Humans, Machine Learning
Adaptive Convolutions for Structure-Aware Style Transfer We propose Adaptive convolutions; a generic extension of AdaIN, which allows for the simultaneous transfer of both statistical and structural styles in real time. June 19, 2021IEEE Conference on Computer...
