Agus Gunawan

I am a Ph.D. student in School of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST), advised by Prof. Munchurl Kim. Before joining KAIST, I received my B.E. in Computer Science from Bandung Institute of Technology (ITB).

My research focuses on low-level computer vision and computational photography. I am especially interested in developing a controllable / user-guided deep-learning network for various low-level computer vision tasks.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Github

profile photo
Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer
Agus Gunawan, Soo Ye Kim, Hyeonjun Sim, Jae-Ho Lee, Munchurl Kim
CVPR, 2023
paper / arXiv / project page / code / video

We present old photo modernization using multiple references by performing stylization and enhancement in a unified manner. In order to modernize old photos, we propose a novel multi-reference-based old photo modernization (MROPM) framework consisting of a network MROPM-Net and a novel synthetic data generation scheme.

Understanding and Improving Group Normalization
Agus Gunawan, Xu Yin, Kang Zhang
Preprint, 2022
arXiv / code

We find that GN's inferior performance against Batch normalization (BN) is caused by: unstable training performance and sensitivity to distortion, whether it comes from external noise or perturbations introduced by the regularization. In addition, we found that GN can only help the neural network training in some specific period, unlike BN, which helps the network throughout the training. To solve these issues, we propose a new normalization layer by combining the benefit of GN and BN.

Test-time Adaptation for Real Image Denoising via Meta-transfer Learning
Agus Gunawan*, Muhammad Adi Nugroho*, Se Jin Park*
Preprint, 2022
arXiv / code

We propose to improve real image denoising performance through a better learning strategy that can enable test-time adaptation on the multi-task network using two-stage learning. The first stage pre-train the network using meta-auxiliary learning to get better meta-initialization. Meanwhile, the second stage is a meta-learning strategy to fine-tune (meta-transfer learning) the network to enable test-time adaptation on real noisy images.

CISRNet: Compressed Image Super-Resolution Network
Agus Gunawan, Sultan R H Madjid
Preprint, 2022
arXiv / code

CISRNet is a coarse-to-fine network for compressed image super-resolution tasks. This network consists of two main subnetworks; the coarse and refinement network, where recursive and residual learning is employed within these two networks respectively.

Key Frame Extraction with Face Biometric Features in Multi-shot Human Re-identification System
Agus Gunawan, Dwi H Widyantoro
ResearchGate / seamls - poster / code

A faster multi-shot person re-identification system with a newly proposed key frame extraction method using face features extracted from a deep learning network.

Acknowledgment: received much help from Holy Lovenia

Professional Experiences

Webpage template from Jon Barron