Senior Staff Scientist

Video Lab, InterDigital
New York, NY 10120


Jiahao Pang  (龐家昊)

I am a Senior Staff Scientist with the Video Lab of InterDigital. Before joining InterDigital in 2019, I was a Senior Researcher with SenseTime. I obtained my Ph.D. in ECE from the Hong Kong University of Science and Technology in 2016.

My research interests center around 3D computer vision, computational photography, graph signal processing, and deep learning. I have 10+ years of research experience in the industry and academia. My research works have been published in top conferences and journals, such as CVPR, ICCV, IEEE T-IP, and accumulated 2500+ citations.

Recent Experiences

  • Senior Staff Scientist
    InterDigital Communications, Inc., New York, U.S., 2019 - Now
  • Senior Researcher
    SenseTime Research, Hong Kong, China, 2016 - 2019
  • Collaborative Research Student
    National Institute of Informatics, Tokyo, Japan, 2015 - 2016

Education

  • Ph.D. in Electronic and Computer Engineering
    Hong Kong University of Science and Technology, 2011 - 2016
  • M.Sc. in Electronic Technology
    Hong Kong University of Science and Technology, 2010 - 2011
  • B.Eng. Electronic Science & Technology
    South China University of Technology, 2006 - 2010

Selected Projects
PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compression
Jiahao Pang, Kevin Bui, Dong Tian, 3DV, 2024
Paper / Supplementary Material / Poster / Slides / Video / Code

 
DDA-Net: Deep Distribution-Aware Network for Point Cloud Compression
Junghyun Ahn, Jiahao Pang, Muhammad Asad Lodhi, Dong Tian, IEEE ISCAS, 2023
Paper / Supplementary Material / Poster / Slides / Video / Code
🚩 Best Paper Award of ISCAS 2023 (VSPC Track)

 
Graph-Based Depth Denoising & Dequantization for Point Cloud Enhancement
Xue Zhang, Gene Cheung, Jiahao Pang, Yash Sanghvi, Abhiram Gnanasambandam, Stanley H. Chan, IEEE T-IP, 2022
Paper / Supplementary Material / Poster / Slides / Video / Code
 
 
GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression
Jiahao Pang, Muhammad Asad Lodhi, Dong Tian, ACM MM Workshop, 2022
Paper / Supplementary Material / Poster / Slides / Video / Code

 
 
TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations
Jiahao Pang, Duanshun Li, Dong Tian, CVPR, 2021
Paper / Supplementary Material / Poster / Slides / Video / Code
🚩 InterDigital Best Paper Award 2022
 
 
FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
Haiyan Wang*, Jiahao Pang*, Muhammad A. Lodhi, Yingli Tian, Dong Tian, CVPR, 2021
Paper / Supplementary Material / Poster / Slides / Video / Code
🚩 Oral Presentation at CVPR 2021
 
 
Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
Wei Hu, Jiahao Pang, Xianming Liu, Dong Tian, Chia-Wen Lin, Anthony Vetro, IEEE T-MM, 2021
Paper / Supplementary Material / Poster / Slides / Video / Code /

 
 
Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Modules
Di Qiu*, Jiahao Pang*, Chengxi Yang, Wenxiu Sun, ICCV, 2019
Paper / Supplementary Material / Poster / Slides / Video / Code

 
 
Deep Graph Laplacian Regularization for Robust Denoising of Real Images
Jin Zeng*, Jiahao Pang*, Wenxiu Sun, Gene Cheung, CVPR Workshop, 2019
Paper / Supplementary Material / Poster / Slides / Video / Code /

 
 
Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
Jiahao Pang, Wenxiu Sun, Chengxi Yang, Jimmy Ren, Ruichao Xiao, Jin Zeng, Liang Lin, CVPR, 2018
Paper / Supplementary Material / Poster / Slides / Video / Code

 
 
Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matchings
Jiahao Pang*, Wenxiu Sun*, Jimmy SJ. Ren, Chengxi Yang, Qiong Yan, ICCV Workshop, 2017
Paper / Supplementary Material / Poster / Slides / Video / Code

 
 
Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain
Jiahao Pang, Gene Cheung, IEEE T-IP, 2017
Paper / Supplementary Material / Poster / Slides / Video / Code

 
 
Subpixel-Based Image Scaling for Grid-like Subpixel Arrangements: A Generalized Continuous-Domain Analysis Model
Jiahao Pang, Lu Fang, Jin Zeng, Yuanfang Guo, Ketan Tang, IEEE T-IP, 2016
Paper / Supplementary Material / Poster / Slides / Video / Code

* Authors contributed equally.