CV

Education

April 2022 - Present: Saarland University
- M.Sc. in Visual Computing.
- Projects:
  - Computer Graphics: Lightwave - Ray Tracer, first prize in the rendering competition.
  - High Level Computer Vision: A damper for overfitting problem in training INR for Image Denoising.
Aug 2017 – Aug 2021: Ho Chi Minh city University of Technology
- B.E. in Computer Science (GPA: 8.58 / 10.0).
- Bachelor Thesis: Image Denoising for Smartphone Cameras.
  Implemented and empirically optimized an encoder-decoder CNN architecture
  Quality: PSNR ≈ 39 in SIDD and DND (SOTA performance)
  Speed: 12MP/s on Snap 855 (× 100 times faster than other SOTA methods)

Oct 2022 - Present: Research Assistant in MPI-INF
Oct 2021 - April 2022: Research Engineer at Graphicsminer
- Working on SLAM (Simultaneous Localization and Mapping) on smartphone.
- Real-Time 3D Tracking on Android.
  - Estimating 6 DOF pose of a rigid object relative to the camera with only an input RGB image (Demo: Single-Object Tracking, Multiple-Object Tracking).
  - Reached 20 fps on Snap 865.
- Real-Time 3D Reconstruction on Android.
  - Creating a 3D model based on RGB image sequence by only using smartphone (Demo).
- Real-Time 3D Object Detection on Android.
  - Detecting 3D bounding box of company’s products in AR environment.
Oct. 2020 – Oct. 2021: Undergraduate Research Assistant at HCMUT
- Self-supervised CNN - based Image Denoising
  - Analysed Stein’s unbiased risk estimate and blind spot networks’ architectures
- Image Denoising for Smartphones
  - Proposed and implemented a denoising model processing a 12MB noisy image within 1 second
Jun 2020 - Oct 2020: Intern at Graphicsminer
- Learning Computer Graphic, Computer Vision.
- Implementing real-time video stabilization algorithm on Android (reached 11 Fps on Pixel 1).