by Sarah Frigg | Oct 11, 2022 | Rendering, Video Processing, Visual Computing
TempFormer: Temporally Consistent Transformer for Video Denoising We propose an efficient hybrid Transformer-based model, TempFormer, which composes SpatioTemporal Transformer Blocks (STTB) and 3D convolutional layers. October 11, 2022European Conference on Computer...
by Sarah Frigg | Oct 5, 2022 | Capture, Machine Learning, VFX
Learning Dynamic 3D Geometry and Texture for Video Face Swapping We approach the problem of face swapping from the perspective of learning simultaneous convolutional facial autoencoders for the source and target identities, using a shared encoder network with...
by Sarah Frigg | Sep 19, 2022 | Rendering, Video Processing, Visual Computing
Automatic Feature Selection for Denoising Volumetric Renderings We propose a method for constructing feature sets that significantly improve the quality of neural denoisers for Monte Carlo renderings with volumetric content. April 7, 2022Eurographics Symposium on...
by Sarah Frigg | Sep 13, 2022 | Capture, Machine Learning, VFX
Facial Animation with Disentangled Identity and Motion using Transformers We propose a 3D+time framework for modeling dynamic sequences of 3D facial shapes, representing realistic non-rigid motion during a performance. September 13, 2022ACM/Eurographics Symposium...
by Sarah Frigg | Jul 25, 2022 | Capture, Machine Learning, VFX
Training a Deep Remastering Model We present a deep learning solution to bring the NTSC version to the new scan quality levels, which would be otherwise impossible with existing tools. July 24, 2022ACM SIGGRAPH 2022 Authors Abdelaziz Djelouah...
