no code implementations • 22 Feb 2024 • Or Patashnik, Rinon Gal, Daniel Cohen-Or, Jun-Yan Zhu, Fernando de la Torre
In this work, we focus on spatial control-based geometric manipulations and introduce a method to consolidate the editing process across various views.
no code implementations • 21 Feb 2024 • Chen Wu, Fernando de la Torre
Text-to-image diffusion models have achieved remarkable performance in image synthesis, while the text interface does not always provide fine-grained control over certain image factors.
1 code implementation • 10 Jan 2024 • Lin Zhang, Linghan Xu, Saman Motamed, Shayok Chakraborty, Fernando de la Torre
Unsupervised domain adaptation (UDA) for image classification has made remarkable progress in transferring classification knowledge from a labeled source domain to an unlabeled target domain, thanks to effective domain alignment techniques.
no code implementations • 6 Dec 2023 • Jianjin Xu, Saman Motamed, Praneetha Vaddamanu, Chen Henry Wu, Christian Haene, Jean-Charles Bazin, Fernando de la Torre
Specifically, we insert parallel attention matrices to each cross-attention module in the denoising network, which attends to features extracted from reference images by an identity encoder.
1 code implementation • ICCV 2023 • Cheng Zhang, Xuanbai Chen, Siqi Chai, Chen Henry Wu, Dmitry Lagun, Thabo Beeler, Fernando de la Torre
We show that, for some attributes, images can represent concepts more expressively than text.
1 code implementation • 24 Apr 2023 • Aashish Rai, Hiresh Gupta, Ayush Pandey, Francisco Vicente Carrasco, Shingo Jason Takagi, Amaury Aubel, Daeil Kim, Aayush Prakash, Fernando de la Torre
By combining 2D face generative models with semantic face manipulation, this method enables editing of detailed 3D rendered faces.
Ranked #5 on 3D Face Reconstruction on REALY (side-view)
2 code implementations • ICCV 2023 • Saman Motamed, Jianjin Xu, Chen Henry Wu, Fernando de la Torre
By using ~40 reference images, PATMAT creates anchor points in MAT's style module, and tunes the model using the fixed anchors to adapt the model to a new face identity.
no code implementations • CVPR 2023 • Jinqi Luo, Zhaoning Wang, Chen Henry Wu, Dong Huang, Fernando de la Torre
Extensive experiments demonstrate that our method is capable of producing counterfactual images and offering sensitivity analysis for model diagnosis without the need for a test set.
no code implementations • 23 Mar 2023 • Jinqi Luo, Zhaoning Wang, Chen Henry Wu, Dong Huang, Fernando de la Torre
Rather than relying on a carefully designed test set to assess ML models' failures, fairness, or robustness, this paper proposes Semantic Image Attack (SIA), a method based on the adversarial attack that provides semantic adversarial images to allow model diagnosis, interpretability, and robustness.
1 code implementation • ICCV 2023 • Shubhra Aich, Jesus Ruiz-Santaquiteria, Zhenyu Lu, Prachi Garg, K J Joseph, Alvaro Fernandez Garcia, Vineeth N Balasubramanian, Kenrick Kin, Chengde Wan, Necati Cihan Camgoz, Shugao Ma, Fernando de la Torre
Our sampling scheme outperforms SOTA methods significantly on two 3D skeleton gesture datasets, the publicly available SHREC 2017, and EgoGesture3D -- which we extract from a publicly available RGBD dataset.
1 code implementation • ICCV 2023 • Chen Henry Wu, Fernando de la Torre
We demonstrate that this latent space of stochastic diffusion models can be used in the same way as that of deterministic diffusion models in two applications.
1 code implementation • 31 Dec 2022 • Jiaqi Geng, Dong Huang, Fernando de la Torre
Advances in computer vision and machine learning techniques have led to significant development in 2D and 3D human pose estimation from RGB cameras, LiDAR, and radars.
3 code implementations • 11 Oct 2022 • Chen Henry Wu, Fernando de la Torre
The commonly-adopted formulation of the latent code of diffusion models is a sequence of gradually denoised samples, as opposed to the simpler (e. g., Gaussian) latent space of GANs, VAEs, and normalizing flows.
1 code implementation • 14 Sep 2022 • Chen Henry Wu, Saman Motamed, Shaunak Srivastava, Fernando de la Torre
Our experiments demonstrate how PromptGen can efficiently sample from several unconditional generative models (e. g., StyleGAN2, StyleNeRF, diffusion autoencoder, NVAE) in a controlled or/and de-biased manner using various off-the-shelf models: (1) with the CLIP model as control, PromptGen can sample images guided by text, (2) with image classifiers as control, PromptGen can de-bias generative models across a set of attributes or attribute combinations, and (3) with inverse graphics models as control, PromptGen can sample images of the same identity in different poses.
1 code implementation • 30 Aug 2022 • Fariborz Taherkhani, Aashish Rai, Quankai Gao, Shaunak Srivastava, Xuanbai Chen, Fernando de la Torre, Steven Song, Aayush Prakash, Daeil Kim
3D face modeling has been an active area of research in computer vision and computer graphics, fueling applications ranging from facial expression transfer in virtual avatars to synthetic data generation.
2 code implementations • ICCV 2021 • Alexander Richard, Michael Zollhoefer, Yandong Wen, Fernando de la Torre, Yaser Sheikh
To improve upon existing models, we propose a generic audio-driven facial animation approach that achieves highly realistic motion synthesis results for the entire face.
Ranked #2 on 3D Face Animation on VOCASET
no code implementations • CVPR 2022 • Amin Jourabloo, Baris Gecer, Fernando de la Torre, Jason Saragih, Shih-En Wei, Te-Li Wang, Stephen Lombardi, Danielle Belko, Autumn Trimble, Hernan Badino
Social presence, the feeling of being there with a real person, will fuel the next generation of communication systems driven by digital humans in virtual reality (VR).
1 code implementation • CVPR 2021 • Shugao Ma, Tomas Simon, Jason Saragih, Dawei Wang, Yuecheng Li, Fernando de la Torre, Yaser Sheikh
Telecommunication with photorealistic avatars in virtual or augmented reality is a promising path for achieving authentic face-to-face communication in 3D over remote physical distances.
no code implementations • CVPR 2021 • Lele Chen, Chen Cao, Fernando de la Torre, Jason Saragih, Chenliang Xu, Yaser Sheikh
This paper addresses previous limitations by learning a deep learning lighting model, that in combination with a high-quality 3D face tracking algorithm, provides a method for subtle and robust facial motion transfer from a regular video to a 3D photo-realistic avatar.
2 code implementations • 11 Mar 2021 • Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, Laszlo A. Jeni, Fernando de la Torre
Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications.
1 code implementation • 2 Nov 2020 • Denis Tome, Thiemo Alldieck, Patrick Peluse, Gerard Pons-Moll, Lourdes Agapito, Hernan Badino, Fernando de la Torre
The quantitative evaluation, on synthetic and real-world datasets, shows that our strategy leads to substantial improvements in accuracy over state of the art egocentric approaches.
no code implementations • ECCV 2020 • Hang Chu, Shugao Ma, Fernando de la Torre, Sanja Fidler, Yaser Sheikh
It is important to note that traditional person-specific CAs are learned from few training samples, and typically lack robustness as well as limited expressiveness when transferring facial expressions.
no code implementations • 11 Aug 2020 • Alexander Richard, Colin Lea, Shugao Ma, Juergen Gall, Fernando de la Torre, Yaser Sheikh
Codec Avatars are a recent class of learned, photorealistic face models that accurately represent the geometry and texture of a person in 3D (i. e., for virtual reality), and are almost indistinguishable from video.
2 code implementations • ECCV 2020 • Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, Laszlo A. Jeni, Fernando de la Torre
3D human shape and pose estimation from monocular images has been an active area of research in computer vision, having a substantial impact on the development of new applications, from activity recognition to creating virtual avatars.
Ranked #71 on 3D Human Pose Estimation on MPI-INF-3DHP
no code implementations • 28 Feb 2020 • Stanislav Panev, Francisco Vicente, Fernando de la Torre, Véronique Prinet
Combining 3D geometric reasoning with advanced vision-based detection methods, our approach is able to estimate the vehicle to curb distance in real time with mean accuracy of more than 90%, as well as its orientation, height and depth.
no code implementations • CVPR 2018 • Jayakorn Vongkulbhisal, Beñat Irastorza Ugalde, Fernando de la Torre, João P. Costeira
Rigid Point Cloud Registration (PCReg) refers to the problem of finding the rigid transformation between two sets of point clouds.
1 code implementation • 17 Nov 2017 • Joachim D. Curtó, Irene C. Zarza, Fernando de la Torre, Irwin King, Michael R. Lyu
Generative Adversarial Networks (GANs) convergence in a high-resolution setting with a computational constrain of GPU memory capacity (from 12GB to 24 GB) has been beset with difficulty due to the known lack of convergence rate stability.
Ranked #1 on Image Generation on CelebA 128x128 (MS-SSIM metric)
no code implementations • ICCV 2017 • Calvin Murdock, Fernando De la Torre
However, methods for subspace learning from subspace-valued data have been notably absent due to incompatibilities with standard problem formulations.
no code implementations • 13 Jul 2017 • Jayakorn Vongkulbhisal, Fernando de la Torre, João P. Costeira
This approach faces two main challenges: (i) designing a cost function with a local optimum at an acceptable solution, and (ii) developing an efficient numerical method to search for one (or multiple) of these local optima.
no code implementations • CVPR 2017 • Calvin Murdock, Fernando de la Torre
Principal component analysis (PCA) is one of the most versatile tools for unsupervised learning with applications ranging from dimensionality reduction to exploratory data analysis and visualization.
no code implementations • CVPR 2017 • Jayakorn Vongkulbhisal, Fernando de la Torre, Joao P. Costeira
This approach faces two main challenges: (1) designing a cost function with a local optimum at an acceptable solution, and (2) developing an efficient numerical method to search for one (or multiple) of these local optima.
no code implementations • CVPR 2017 • Dong Huang, Longfei Han, Fernando de la Torre
However, existing divide-and-conquer approaches fail to deal with discontinuities between partitions (e. g., Gaussian mixture of regressions) and they cannot guarantee that the partitioned input space will be homogeneously modeled by local regressors (e. g., ordinal regression).
1 code implementation • 27 Feb 2017 • Joachim D. Curtó, Irene C. Zarza, Feng Yang, Alexander J. Smola, Fernando de la Torre, Chong-Wah Ngo, Luc van Gool
The algorithm requires to compute the product of Walsh Hadamard Transform (WHT) matrices.
no code implementations • 7 Dec 2016 • Enrique Sánchez-Lozano, Georgios Tzimiropoulos, Brais Martinez, Fernando de la Torre, Michel Valstar
This paper presents a Functional Regression solution to the least squares problem, which we coin Continuous Regression, resulting in the first real-time incremental face tracker.
no code implementations • 21 Nov 2016 • Ramon Sanabria, Florian Metze, Fernando de la Torre
Speech is one of the most effective ways of communication among humans.
no code implementations • 2 Aug 2016 • Wen-Sheng Chu, Fernando de la Torre, Jeffrey F. Cohn
To model temporal dependencies, Long Short-Term Memory (LSTMs) are stacked on top of these representations, regardless of the lengths of input videos.
no code implementations • CVPR 2016 • Jayakorn Vongkulbhisal, Ricardo Cabral, Fernando de la Torre, Joao P. Costeira
Object detection has been a long standing problem in computer vision, and state-of-the-art approaches rely on the use of sophisticated features and/or classifiers.
no code implementations • ICCV 2015 • Calvin Murdock, Fernando de la Torre
If weakly-supervised information is available in the form of image-level tags, SCA factorizes a set of images into semantic groups of superpixels.
no code implementations • ICCV 2015 • Jiabei Zeng, Wen-Sheng Chu, Fernando de la Torre, Jeffrey F. Cohn, Zhang Xiong
Varied sources of error contribute to the challenge of facial action unit detection.
no code implementations • ICCV 2015 • Wen-Sheng Chu, Jiabei Zeng, Fernando de la Torre, Jeffrey F. Cohn, Daniel S. Messinger
We evaluate the effectiveness of our approach in multiple databases, including human actions using the CMU Mocap dataset, spontaneous facial behaviors using group-formation task dataset and parent-infant interaction dataset.
no code implementations • CVPR 2015 • Kaili Zhao, Wen-Sheng Chu, Fernando de la Torre, Jeffrey F. Cohn, Honggang Zhang
The most commonly used taxonomy to describe facial behaviour is the Facial Action Coding System (FACS).
no code implementations • CVPR 2015 • Xuehan Xiong, Fernando de la Torre
It is generally accepted that second order descent methods are the most robust, fast, and reliable approaches for nonlinear optimization of a general smooth function.
no code implementations • 27 Feb 2015 • Miguel Angel Bautista, Oriol Pujol, Fernando de la Torre, Sergio Escalera
To address these limitations this paper proposes an Error-Correcting Factorization (ECF) method, our contribution is three fold: (I) We propose a novel representation of the error-correction capability, called the design matrix, that enables us to build an ECOC on the basis of allocating correction to pairs of classes.
no code implementations • 20 Jul 2014 • Ji Zhao, Lian-Tao Wang, Ricardo Cabral, Fernando de la Torre
There are four main benefits of our approach: (1) Our approach accommodates non-linear additive kernels such as the popular $\chi^2$ and intersection kernel; (2) our approach is able to handle both regions in images and spatio-temporal regions in videos in a unified way; (3) the feature selection problem is convex, and both problems can be solved using a scalable reduced gradient method; (4) we point out strong connections with multiple kernel learning and multiple instance learning approaches.
no code implementations • CVPR 2014 • Yingying Zhu, Dong Huang, Fernando de la Torre, Simon Lucey
The task of estimating complex non-rigid 3D motion through a monocular camera is of increasing interest to the wider scientific community.
no code implementations • 3 May 2014 • Xuehan Xiong, Fernando de la Torre
Using generic descent maps, we derive a practical algorithm - Supervised Descent Method (SDM) - for minimizing Nonlinear Least Squares (NLS) problems.
no code implementations • CVPR 2013 • Feng Zhou, Fernando de la Torre
This paper proposes deformable graph matching (DGM), an extension of GM for matching graphs subject to global rigid and non-rigid geometric constraints.
no code implementations • CVPR 2013 • Wen-Sheng Chu, Fernando de la Torre, Jeffery F. Cohn
To evaluate the effectiveness of STM, we compared STM to generic classifiers and to cross-domain learning methods in three major databases: CK+ [20], GEMEP-FERA [32] and RU-FACS [2].
no code implementations • CVPR 2013 • Xuehan Xiong, Fernando de la Torre
It is generally accepted that 2 nd order descent methods are the most robust, fast and reliable approaches for nonlinear optimization of a general smooth function.
Ranked #33 on Face Alignment on WFLW