Hoang Trieu Vy LE

I'm currently a Principal AI Research And Development Engineer at BeinkDream, where I mainly work on computer visions tasks and generative AI.

I received the Ph.D degree in Signal & Image Processing from ENS Lyon in 2023 under the warm and insightful supervision of Nelly Pustelnik and Marion Foare.

My current research mainly lies on developing general learning algorithms for different tasks in computer vision.

Email  /  CV  /  Scholar  /  Github /  Linkedin

Research

My research topics include unfolded Neural Networks, computer vision , deep learning, generative AI, and image processing.

In this paper, we present a new edge detection model based on proximal unfolded neural networks. The architecture relies on unfolding proximal Blake-Zisserman iterations, leading to a composition of two blocks: a smoothing block and an edge detection block.

@ARTICLE{10630640,
  author={Le, Hoang Trieu Vy and Repetti, Audrey and Pustelnik, Nelly},
  journal={IEEE Transactions on Image Processing}, 
  title={Unfolded Proximal Neural Networks for Robust Image Gaussian Denoising}, 
  year={2024},
  volume={33},
  number={},
  pages={4475-4487},
  doi={10.1109/TIP.2024.3437219}}

We propose different learning strategies for our PNN framework, and investigate their robustness (Lipschitz property) and denoising efficiency. Finally, we assess the robustness of our PNNs when plugged in a forward-backward algorithm for an image deblurring problem

@ARTICLE{9723590,
  author={Le, Hoang Trieu Vy and Foare, Marion and Pustelnik, Nelly},
  journal={IEEE Signal Processing Letters}, 
  title={Proximal Based Strategies for Solving Discrete Mumford-Shah 
        With Ambrosio-Tortorelli Penalization on Edges}, 
  year={2022},
  volume={29},
  number={},
  pages={952-956},
  doi={10.1109/LSP.2022.3155307}}

This work is dedicated to joint image restoration and contour detection considering the Ambrosio-Tortorelli functional. Two proximal alternating minimization schemes with convergence guarantees are provided, PALM-AT and SL-PAM-AT, as well as closed-form expressions of the involved proximity operators.

@INPROCEEDINGS{9909592,
  author={Le, Hoang Trieu Vy and Pustelnik, Nelly and Foare, Marion},
  booktitle={2022 30th European Signal Processing Conference (EUSIPCO)}, 
  title={The faster proximal algorithm, the better unfolded deep learning architecture ? 
    The study case of image denoising}, 
  year={2022},
  pages={947-951},
  doi={10.23919/EUSIPCO55093.2022.9909592}}

In this work, we proposed two deep unfolded networks for gaussian denoising that can be activated from standard or accelerated schemes to illustrate the benefit to unroll accelerated schemes when possible.

@inproceedings{HoangTVL2022AlgorithmesPR,
  title={Fast Proximal Unrolled Algorithms for the Analysis of Piecewise Homogeneous Fractal Images},
  author={ Hoang T.V Le, Barbara Pascal, Nelly Pustelnik, Marion Foare and Patrice Abry},
  year={2022},
  url={https://api.semanticscholar.org/CorpusID:253115164}
}

We propose two unrolled deep network architectures built from the proximal FISTA and Chambolle-Pock algorithms to estimate local regularity in piecewise homogeneous fractal images.

Ph.D Thesis

I did my PhD thesis under the supervision of Nelly Pustelnik and Marion Foare at Laboratoire de Physique in École Normale Supérieure de Lyon, France. I worked on the interface between proximal optimisation and Deep Learning approaches to tackle joint image reconstruction and edge detection or segmentation tasks.

Talks

Teaching

This website takes the template from Jon Barron and borrows some ideas from V.N Nguyen.