research
∙
12/02/2022
QC-StyleGAN – Quality Controllable Image Generation and Manipulation
The introduction of high-quality image generation models, particularly t...
share
research
∙
10/28/2022
Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis
Recently, great progress has been made in 3D deep learning with the emer...
research
∙
05/10/2022
Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey
The existence of representative datasets is a prerequisite of many succe...
research
∙
12/01/2021
HyperInverter: Improving StyleGAN Inversion via Hypernetwork
Real-world image manipulation has achieved fantastic progress in recent ...
research
∙
10/18/2021
Exploiting Domain-Specific Features to Enhance Domain Generalization
Domain Generalization (DG) aims to train a model, from multiple observed...
research
∙
09/06/2021
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images
Recovering the 3D structure of an object from a single image is a challe...
research
∙
02/02/2018
ExpNet: Landmark-Free, Deep, 3D Facial Expressions
We describe a deep learning based method for estimating 3D facial expres...
research
∙
12/14/2017
Extreme 3D Face Reconstruction: Looking Past Occlusions
Existing single view, 3D face reconstruction methods can produce beautif...
research
∙
08/24/2017
FacePoseNet: Making a Case for Landmark-Free Face Alignment
We show how a simple convolutional neural network (CNN) can be trained t...
research
∙
12/15/2016
Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
The 3D shapes of faces are well known to be discriminative. Yet despite ...
research
∙
03/23/2016