Our Research

Research

MMLab@NTU

Members in MMLab@NTU conduct research primarily in low-level vision, image and video understanding, creative content creation, 3D scene understanding and reconstruction.

Super-Resolution

Our team is the first to introduce the use of deep neural networks to directly predict super-resolved images. Our journal paper on image super-resolution was selected as the `Most Popular Article' by IEEE Transactions on Pattern Analysis and Machine Intelligence in 2016. It remains as one of the top 10 articles to date. Popular image and video super-resolution methods developed by our team include SRCNN, ESRGAN, EDVR, GLEAN and BasicVSR.

Content Editing and Generation

We research new methods for generating high-resolution, realistic and novel contents in images and videos. We are also interested in investigating fundamental concepts in generative models. Some of our works include scene deocclusion, video inpainting, image generation, and image manipulation.

Image and Video Understanding

We explore effective and efficient methods to detect, segment and recognize objects in complex scenes. We were the champion in COCO 2019 Object Detection Challenge 2019, and Open Images Challenge 2019.

3D Scene Understanding

Our team has been working on various tasks related to 3D reconstruction and perception, e.g, 3D shape generation and 3D human recovery. Check out our recent work on Variational Relational Point Completion Network, Unsupervised 3D Shape Completion through GAN Inversion and LiDAR-based Panoptic Segmentation.

Deep Learning

We investigate new deep learning methods that are more efficient, robust, accurate, scalable, transferable, and explainable. We have been working on various problems like domain generalization, knowledge distillation, long-tailed recognition, and self-supervised learning. We participated in Facebook AI Self-Supervision Challenge 2019, and we won champions of all four tracks. Check out OpenSelfSup, our open-source project for self-supervised learning.

Media Forensics

The popularization of Deepfakes on the internet has set off alarm bells among the general public and authorities, in view of the conceivable perilous implications. We have proposed two large-scale datasets for face forgery detection. See DeeperForensics and ForgeryNet.

Research

Video Demos

deocclusion
Scene De-occlusion
faceoff
Face Swapping
faceoff
Pareidolia Face Reenactment
faceoff
Effect Interpolation
faceoff
Video Inpainting
singan_bohemian
Image Generation and Extrapolation
singan_bohemian
Low-Light Image Enhancement
faceoff
Point Cloud Completion
faceoff
Image Restoration and Manipulation
faceoff
Optical Flow Estimation
faceoff
Audio-Driven Face Reenactment
faceoff
Motion Retargeting
faceoff
Anime Super-Resolution (Credit: Jan Bing)
faceoff
Game Super-Resolution (Credit: Snouz)
faceoff
Anime Video Interpolation

Selected

Media Coverage | Blog

Source: @Luke_Aaron