no code implementations • 6 Feb 2024 • Alfredo Rivero, ShahRukh Athar, Zhixin Shu, Dimitris Samaras
Using a set of control signals, such as head pose and expressions, we transform them to the 3D space with learned deformations to generate the desired rendering.
no code implementations • 21 Dec 2023 • Artem Sevastopolsky, Philip-William Grassal, Simon Giebenhain, ShahRukh Athar, Luisa Verdoliva, Matthias Niessner
The decomposition of the parametric model and high-quality vertex displacements allows us to animate the model and modify it semantically.
no code implementations • 20 Sep 2023 • ShahRukh Athar, Zhixin Shu, Zexiang Xu, Fujun Luan, Sai Bi, Kalyan Sunkavalli, Dimitris Samaras
The surface normals prediction is guided using 3DMM normals that act as a coarse prior for the normals of the human head, where direct prediction of normals is hard due to rigid and non-rigid deformations induced by head-pose and facial expression changes.
no code implementations • CVPR 2022 • ShahRukh Athar, Zexiang Xu, Kalyan Sunkavalli, Eli Shechtman, Zhixin Shu
In this work, we propose RigNeRF, a system that goes beyond just novel view synthesis and enables full control of head pose and facial expressions learned from a single portrait video.
no code implementations • 28 Oct 2021 • ShahRukh Athar, Zhou Wang
In practical media distribution systems, visual content usually undergoes multiple stages of quality degradation along the delivery chain, but the pristine source content is rarely available at most quality monitoring points along the chain to serve as a reference for quality assessment.
1 code implementation • 16 Oct 2021 • Raymond Zhou, ShahRukh Athar, Zhongling Wang, Zhou Wang
Banding or false contour is an annoying visual artifact whose impact is even more pronounced in ultra high definition, high dynamic range, and wide colour gamut visual content, which is becoming increasingly popular.
no code implementations • 29 Sep 2021 • ShahRukh Athar, Albert Pumarola, Francesc Moreno-Noguer, Dimitris Samaras
Facial Expressions induce a variety of high-level details on the 3D face geometry.
no code implementations • 29 Sep 2021 • ShahRukh Athar, Zhixin Shu, Dimitris Samaras
In this work, we design a system that enables 1) novel view synthesis for portrait video, of both the human subject and the scene they are in and 2) explicit control of the facial expressions through a low-dimensional expression representation.
no code implementations • 24 Sep 2021 • ShahRukh Athar, Zhongling Wang, Zhou Wang
This casts great challenges to deep neural network (DNN) based blind IQA (BIQA), which requires large-scale training data that is representative of the natural image distribution.
no code implementations • 11 Aug 2021 • Aggelina Chatziagapi, ShahRukh Athar, Francesc Moreno-Noguer, Dimitris Samaras
We present SIDER(Single-Image neural optimization for facial geometric DEtail Recovery), a novel photometric optimization method that recovers detailed facial geometry from a single image in an unsupervised manner.
no code implementations • 10 Aug 2021 • ShahRukh Athar, Zhixin Shu, Dimitris Samaras
In this work, we design a system that enables both novel view synthesis for portrait video, including the human subject and the scene background, and explicit control of the facial expressions through a low-dimensional expression representation.
no code implementations • 14 Dec 2020 • ShahRukh Athar, Albert Pumarola, Francesc Moreno-Noguer, Dimitris Samaras
The facial details are represented as a vertex displacement map and used then by a Neural Renderer to photo-realistically render novel images of any single image in any desired expression and view.
no code implementations • ICCV 2021 • Jingyi Xu, Hieu Le, Mingzhen Huang, ShahRukh Athar, Dimitris Samaras
We assume that the distribution of intra-class variance generalizes across the base class and the novel class.
Ranked #14 on Few-Shot Image Classification on CUB 200 5-way 5-shot
no code implementations • 2 Nov 2019 • ShahRukh Athar, Zhixin Shu, Dimitris Samaras
In the "motion-editing" step, we explicitly model facial movement through image deformation, warping the image into the desired expression.
1 code implementation • ICLR 2019 • ShahRukh Athar, Evgeny Burnaev, Victor Lempitsky
The learning process provides a latent embedding for every image in the training dataset, as well as a deep convolutional network that maps the latent space to the image space.