no code implementations • CVPR 2023 • Takehiko Ohkawa, Kun He, Fadime Sener, Tomas Hodan, Luan Tran, Cem Keskin
To obtain high-quality 3D hand pose annotations for the egocentric images, we develop an efficient pipeline, where we use an initial set of manual annotations to train a model to automatically annotate a much larger dataset.
no code implementations • CVPR 2023 • Shreyas Hampali, Tomas Hodan, Luan Tran, Lingni Ma, Cem Keskin, Vincent Lepetit
As direct optimization over all shape and pose parameters is prone to fail without coarse-level initialization, we propose an incremental approach that starts by splitting the sequence into carefully selected overlapping segments within which the optimization is likely to succeed.
no code implementations • 31 Oct 2022 • Shangchen Han, Po-Chen Wu, Yubo Zhang, Beibei Liu, Linguang Zhang, Zheng Wang, Weiguang Si, Peizhao Zhang, Yujun Cai, Tomas Hodan, Randi Cabezas, Luan Tran, Muzaffer Akbay, Tsz-Ho Yu, Cem Keskin, Robert Wang
In this paper, we present a unified end-to-end differentiable framework for multi-view, multi-frame hand tracking that directly predicts 3D hand pose in world space.
no code implementations • 30 Jul 2022 • Lin Huang, Tomas Hodan, Lingni Ma, Linguang Zhang, Luan Tran, Christopher Twigg, Po-Chen Wu, Junsong Yuan, Cem Keskin, Robert Wang
Unlike classical correspondence-based methods which predict 3D object coordinates at pixels of the input image, the proposed method predicts 3D object coordinates at 3D query points sampled in the camera frustum.
1 code implementation • CVPR 2021 • Feng Liu, Luan Tran, Xiaoming Liu
That is, for a 2D image of a generic object, we decompose it into latent representations of category, shape and albedo, lighting and camera projection matrix, decode the representations to segmented 3D shape and albedo respectively, and fuse these components to render an image well approximating the input image.
no code implementations • 5 Sep 2019 • Ziyuan Zhang, Luan Tran, Feng Liu, Xiaoming Liu
The LSTM integrates pose features over time as a dynamic gait feature while canonical features are averaged as a static gait feature.
no code implementations • CVPR 2019 • Ziyuan Zhang, Luan Tran, Xi Yin, Yousef Atoum, Xiaoming Liu, Jian Wan, Nanxin Wang
Most of the existing gait recognition methods take silhouettes or articulated body models as the gait features.
no code implementations • CVPR 2019 • Luan Tran, Feng Liu, Xiaoming Liu
By improving the nonlinear 3D morphable model in both learning objective and network architecture, we present a model which is superior in capturing higher level of details than the linear or its precedent nonlinear counterparts.
Ranked #23 on 3D Face Reconstruction on REALY
1 code implementation • ICCV 2019 • Feng Liu, Luan Tran, Xiaoming Liu
Traditional 3D face models learn a latent representation of faces using linear subspaces from limited scans of a single database.
1 code implementation • 28 Aug 2018 • Luan Tran, Xiaoming Liu
To address these problems, this paper proposes an innovative framework to learn a nonlinear 3DMM model from a large set of in-the-wild face images, without collecting 3D face scans.
1 code implementation • ICCV 2019 • Bangjie Yin, Luan Tran, Haoxiang Li, Xiaohui Shen, Xiaoming Liu
Deep CNNs have been pushing the frontier of visual recognition over past years.
1 code implementation • CVPR 2018 • Luan Tran, Xiaoming Liu
As a classic statistical model of 3D facial shape and texture, 3D Morphable Model (3DMM) is widely used in facial analysis, e. g., model fitting, image synthesis.
Ranked #2 on Face Alignment on AFLW2000
1 code implementation • CVPR 2019 • Luan Tran, Kihyuk Sohn, Xiang Yu, Xiaoming Liu, Manmohan Chandraker
Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels.
no code implementations • CVPR 2017 • Luan Tran, Xiaoming Liu, Jiayu Zhou, Rong Jin
To leverage the valuable information in the corrupted data, we propose to impute the missing data by leveraging the relatedness among different modalities.
no code implementations • CVPR 2017 • Luan Tran, Xi Yin, Xiaoming Liu
The large pose discrepancy between two face images is one of the key challenges in face recognition.
no code implementations • 31 May 2017 • Luan Tran, Xi Yin, Xiaoming Liu
First, the encoder-decoder structure of the generator enables DR-GAN to learn a representation that is both generative and discriminative, which can be used for face image synthesis and pose-invariant face recognition.