Hong-En Chen

email: b08901058 [at]

ntu [dot] edu [dot] tw

I am an undergraduate student major in Electrical Engineering at National Taiwan University. Currently, I am researching high quality 3D asset synthesis by deep learning at the Vision and Learning Laboratory directed by Prof. Yu-Chiang Frank Wang.

Meanwhile, I served as visiting scholar at Prof. Tsui-Wei (Lily) Weng’s Trustworthy Machine Learning Lab in UCSD. My main focus is on developing interpretation strategy to explain the profound behaviors of neuron in computer vision models.

Finally, I’m working as a leader for Prof. Lin-shan Lee’s biography website(Digital Archive). With a focus on project maintenance, my expertise lies in infrastructure setup, CI/CD deployment, and team collaboration.

My research interests include high quality 3D asset generation, network dissection and understanding, applications of computer vision models on embedded systems.

Selected Publications

2023

TPA3D: Triplane Attention for Fast Text-to-3D Generation

Hong-En Chen, Bin-Shih Wu, Sheng-Yu Huang, and 1 more author

Submitted to CVPR’24, 2023

Abs HTML PDF

Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization time for both training and inference, the use of GAN-based models would still be desirable for fast 3D generation. In this work, we propose Triplane Attention for text-guided 3D generation (TPA3D), an end-to-end trainable GAN-based deep learning model for fast text-to-3D generation. With only 3D shape data and their rendered 2D images observed during training, our TPA3D is designed to retrieve detailed visual descriptions for synthesizing the corresponding 3D mesh data. This is achieved by the proposed attention mechanisms on the extracted sentence and word-level text features. In our experiments, we show that TPA3D generates high-quality 3D textured shapes aligned with fine-grained descriptions, while impressive computation efficiency can be observed.

2022

UltraBat: An Interactive 3D Side-Scrolling Game Using Ultrasound Levitation

Wei-Hsin Wang, Hong-En Chen, and Mike Y. Chen

In User Interface Software and Technology, 2022

Abs HTML PDF

We present UltraBat, an interactive 3D side-scrolling game inspired by Flappy Bird, in which the game character, a bat, is physically levitated in mid-air using ultrasound. Players aim to navigate the bat through a stalagmite tunnel that scrolls to one side as the bat travels, which is implemented using a pin-array display to create a shape-changing passage.