1 code implementation • 3 Jan 2024 • Evonne Ng, Javier Romero, Timur Bagautdinov, Shaojie Bai, Trevor Darrell, Angjoo Kanazawa, Alexander Richard
We present a framework for generating full-bodied photorealistic avatars that gesture according to the conversational dynamics of a dyadic interaction.
no code implementations • 14 Nov 2023 • Wojciech Zielonka, Timur Bagautdinov, Shunsuke Saito, Michael Zollhöfer, Justus Thies, Javier Romero
We present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats.
no code implementations • 9 Oct 2023 • Donglai Xiang, Fabian Prada, Zhe Cao, Kaiwen Guo, Chenglei Wu, Jessica Hodgins, Timur Bagautdinov
Clothing is an important part of human appearance but challenging to model in photorealistic avatars.
no code implementations • ICCV 2023 • Shih-Yang Su, Timur Bagautdinov, Helge Rhodin
Previous methods avoid using a template but rely on a costly or ill-posed mapping from observation to canonical space.
no code implementations • CVPR 2023 • Shun Iwase, Shunsuke Saito, Tomas Simon, Stephen Lombardi, Timur Bagautdinov, Rohan Joshi, Fabian Prada, Takaaki Shiratori, Yaser Sheikh, Jason Saragih
To achieve generalization, we condition the student model with physics-inspired illumination features such as visibility, diffuse shading, and specular reflections computed on a coarse proxy geometry, maintaining a small computational overhead.
no code implementations • 20 Jul 2022 • Edoardo Remelli, Timur Bagautdinov, Shunsuke Saito, Tomas Simon, Chenglei Wu, Shih-En Wei, Kaiwen Guo, Zhe Cao, Fabian Prada, Jason Saragih, Yaser Sheikh
To circumvent this, we propose a novel volumetric avatar representation by extending mixtures of volumetric primitives to articulated objects.
no code implementations • 30 Jun 2022 • Donglai Xiang, Timur Bagautdinov, Tuur Stuyck, Fabian Prada, Javier Romero, Weipeng Xu, Shunsuke Saito, Jingfan Guo, Breannan Smith, Takaaki Shiratori, Yaser Sheikh, Jessica Hodgins, Chenglei Wu
The key idea is to introduce a neural clothing appearance model that operates on top of explicit geometry: at training time we use high-fidelity tracking, whereas at animation time we rely on physically simulated geometry.
no code implementations • 7 Jun 2022 • Oshri Halimi, Fabian Prada, Tuur Stuyck, Donglai Xiang, Timur Bagautdinov, He Wen, Ron Kimmel, Takaaki Shiratori, Chenglei Wu, Yaser Sheikh
Here, we propose an end-to-end pipeline for building drivable representations for clothing.
no code implementations • 3 May 2022 • Shih-Yang Su, Timur Bagautdinov, Helge Rhodin
While a few such approaches exist, those have limited generalization capabilities and are prone to learning spurious (chance) correlations between irrelevant body parts, resulting in implausible deformations and missing body parts on unseen poses.
1 code implementation • 25 Mar 2022 • Ziqian Bai, Timur Bagautdinov, Javier Romero, Michael Zollhöfer, Ping Tan, Shunsuke Saito
In this work, for the first time, we enable autoregressive modeling of implicit avatars.
no code implementations • 28 Jun 2021 • Donglai Xiang, Fabian Prada, Timur Bagautdinov, Weipeng Xu, Yuan Dong, He Wen, Jessica Hodgins, Chenglei Wu
To address these difficulties, we propose a method to build an animatable clothed body avatar with an explicit representation of the clothing on the upper body from multi-view captured videos.
no code implementations • 20 Jun 2021 • Benoit Guillard, Edoardo Remelli, Artem Lukoianov, Stephan R. Richter, Timur Bagautdinov, Pierre Baque, Pascal Fua
Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field.
no code implementations • 21 May 2021 • Timur Bagautdinov, Chenglei Wu, Tomas Simon, Fabian Prada, Takaaki Shiratori, Shih-En Wei, Weipeng Xu, Yaser Sheikh, Jason Saragih
The core intuition behind our method is that better drivability and generalization can be achieved by disentangling the driving signals and remaining generative factors, which are not available during animation.
1 code implementation • CVPR 2021 • Ziyan Wang, Timur Bagautdinov, Stephen Lombardi, Tomas Simon, Jason Saragih, Jessica Hodgins, Michael Zollhöfer
In addition, we show that the learned dynamic radiance field can be used to synthesize novel unseen expressions based on a global animation code.
3 code implementations • CVPR 2021 • Nikita Durasov, Timur Bagautdinov, Pierre Baque, Pascal Fua
Our central intuition is that there is a continuous spectrum of ensemble-like models of which MC-Dropout and Deep Ensembles are extreme examples.
1 code implementation • NeurIPS 2020 • Edoardo Remelli, Artem Lukoianov, Stephan R. Richter, Benoît Guillard, Timur Bagautdinov, Pierre Baque, Pascal Fua
Unfortunately, these methods are often not suitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying implicit field.
no code implementations • CVPR 2018 • Tatjana Chavdarova, Pierre Baqué, Stéphane Bouquet, Andrii Maksai, Cijo Jose, Timur Bagautdinov, Louis Lettry, Pascal Fua, Luc van Gool, François Fleuret
People detection methods are highly sensitive to occlusions between pedestrians, which are extremely frequent in many situations where cameras have to be mounted at a limited height.
no code implementations • CVPR 2018 • Timur Bagautdinov, Chenglei Wu, Jason Saragih, Pascal Fua, Yaser Sheikh
We propose a method for learning non-linear face geometry representations using deep generative models.
no code implementations • CVPR 2017 • Timur Bagautdinov, Alexandre Alahi, François Fleuret, Pascal Fua, Silvio Savarese
We present a unified framework for understanding human social behaviors in raw image sequences.
Ranked #2 on Action Recognition on Volleyball
no code implementations • CVPR 2016 • Pierre Baqué, Timur Bagautdinov, François Fleuret, Pascal Fua
Mean-field variational inference is one of the most popular approaches to inference in discrete random fields.
no code implementations • CVPR 2015 • Timur Bagautdinov, Francois Fleuret, Pascal Fua
We propose a novel approach to computing the probabilities of presence of multiple and potentially occluding objects in a scene from a single depth map.