Tianyuan Zhang 「张天远」

I am a second-year master student in Robotics Institute at CMU, supervised by Prof. Srinivasa Narasimhan. Previously, I finished my undergraduate in School of EECS at Peking University, working with Prof. Zhanxing Zhu , and Prof. Hang Zhao.

I work on computational imaging, and computer vision.

Email: tianyuaz [at] andrew [dot] cmu [dot] edu

CV  /  Google Scholar  /  Github /  Portfolio     

profile photo
Research

I'm interested in physiscs-based vision, computational imaging and computer graphics.

Real-Time Intermediate Flow Estimation for Video Frame Interpolation
Zhewei Huang, Tianyuan Zhang, Wen Heng, Boxin Shi, Shuchang Zhou
ECCV, 2022
github / arXiv / demos

We propose a real-time intermediate flow estimation (RIFE) method for video frame interpolation, it runs 30+FPS for 2X 720p interpolation on a 2080Ti GPU

Embracing Single Stride 3D Object Detector with Sparse Transformer
Lue Fan, Ziqi Pang, Tianyuan Zhang, Yu-Xiong Wang, Hang Zhao, Feng Wang, Naiyang Wang, Zhaoxiang Zhang
CVPR, 2022
github / arxiv /

In contrast to 2D, object size in 3D does not exhibit long-tail distributions. We propose a single stride sparse Transformer (SST) for 3D object detection. We obtained impressive results on small objects

DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries
Yue Wang, Vitor Guizilini*, Tianyuan Zhang*, Yilun Wang, Hang Zhao, Justin Solomon
CoRL, 2021
github / arxiv /

A new paradigm of 3D object detection from multiview 2D images

MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries
Tianyuan Zhang, Xuanyao Chen, Yue Wang, Yilun Wang, Hang Zhao
preprint, 2022
project page / github / arXiv

End-to-End 3D tracking with multiview-cameras

FUTR3D: A Unified Sensor Fusion Framework for 3D Detection
Xuanyao Chen, Tianyuan Zhang, Yue Wang, Yilun Wang, Hang Zhao
preprint, 2022
project page / github / arXiv

A unified framework for 3D detection from multi-sensor data. We achieved impressive results with multiview-cameras and one-beam LiDAR.

Objects365: A Large-scale, High-quality Dataset for Object Detection
Shuai Shao*, Zeming Li*, Tianyuan Zhang*, Chao Peng*, Gang Yu, Xiangyu Zhang, Jing Li, Jian Sun
ICCV, 2019
project page / paper

We provide a high-quality large-scale object detection dataset, with 365 categories, 638K images, and 10,101K bounding boxes

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
Dinghuai Zhang*, Tianyuan Zhang*, Yiping Lu*, Zhanxing Zhu, Bin Dong
NeurIPS, 2019  
arXiv / code

Accelerating adversarial training using Pontryagin`s Maximum Principle

Interpreting Adversarially Trained Convolutional Neural Networks
Tianyuan Zhang, Zhanxing Zhu
ICML, 2019
github / arXiv

Discussion on the shape-bias and texture-bias of adversarially trainined convolutional neural networks

Professional Services

Program Committee member / Reviewer: CVPR' 2021, NeurIPS' 2020, ICLR' 2021



Updated at Nov. 2022