by Martina Megaro | Nov 30, 2021 | Video Processing, Visual Computing
Neural Frame Interpolation for Rendered Content We propose solutions for leveraging auxiliary features to obtain better motion estimates, more accurate occlusion handling, and to correctly reconstruct non-linear motion between keyframes. November 30, 2021ACM...
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...
by Martina Megaro | May 8, 2021 | Video Processing, Visual Computing
Lossy Image Compression with Normalizing Flows We propose a deep image compression method that is similarly able to go from low bit-rates to near lossless quality, byleveraging normalizing flows to learn a bijective mapping from the image space toa latent...
