Wen Jiang

Hey! I am a PhD candidate at the department of Computer and Information Science at the University of Pennsylvania and my advisor is Prof. Kostas Daniilidis. Before that, I got my bachelor's degree at Zhejiang University, where I worked with Prof. Xiaowei Zhou. I was fortunate to work as a Machine Learning Intern at the 3D Vision Team for Apple Maps, a Research Scientist Intern at Meta Reality Lab, and a Visiting Fellow at Microsoft Research Asia.

Email  /  Google Scholar  /  GitHub /  LinkedIn

profile photo
Research

AG-SLAM: Active Gaussian Splatting SLAM
Wen Jiang*,  Boshu Lei*,  Katrina AshtonKostas Daniilidis
arxiv preprint, 2024
arxiv / code(comming)

An active Gaussian Splatting SLAM system with active exploration strategy, more accurate mapping and localization

Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting
Matthew Strong*,  Boshu Lei*,  Aiden SwannWen JiangKostas DaniilidisMonroe Kennedy III
arxiv preprint, 2024
Project Page arxiv / code / video

We propose a framework for active next best view and touch selection for robotic manipulators using 3D Gaussian Splatting (3DGS)

Beyond Uncertainty: Risk-Aware Active View Acquisition for Safe Robot Navigation and 3D Scene Understanding with FisherRF
Guangyi Liu*,  Wen Jiang*,  Boshu Lei*,  Kostas DaniilidisNader Motee
arxiv preprint, 2024
arxiv / Bibtex

We introduce a novel approach to enhance robot navigation safety and improve 3D scene understanding by extending beyond conventional uncertainty-based methods.

FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Informations
Wen JiangBoshu LeiKostas Daniilidis
ECCV Oral, 2024
Project Page / arxiv / Code / Bibtex

FisherRF compute the Fihser Information for 3D Gaussian Splatting and other Radiance Fields and could select next best views or quantify pixel-wise uncertainty for its renderings.

Event-based Continuous Color Video Decompression from Single Frames
Ziyun WangFriedhelm HamannKenneth ChaneyWen JiangGuillermo GallegoKostas Daniilidis
arxiv preprint, 2023
Project Page / arxiv / Paper / Bibtex

We propose a novel task called event-based continuous color video decompression , pairing single static color frames and events to reconstruct temporally continuous videos.

Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAE
Wen JiangKostas Daniilidis
arxiv preprint, 2022
arxiv / Code(coming soon) / Bibtex

We propose a novel method for 3D shape completion from a partial observation of a point cloud.

Fast and Robust Multi-Person 3D Pose Estimation and Tracking from Multiple Views
Junting Dong Qi FangWen Jiang Yurou YangQixing HuangHujun BaoXiaowei Zhou
T-PAMI, 2021
Project page / Supplementary / Code / Bibtex

Coherent Reconstruction of Multiple Humans from a Single Image
Wen Jiang*,   Nikos Kolotouros*,   Georgios Pavlakos,   Xiaowei Zhou,   Kostas Daniilidis
CVPR, 2020  
Project Page / Paper / Code / Bibtex

End-to-end reconstruction of multiple people using two novel geometric losses that encourage coherent 3D estimates

Deep Snake for Real-Time Instance Segmentation
Sida PengWen JiangHuaijin PiHujun BaoXiaowei Zhou
CVPR, 2020 Oral presentation 
Arxiv / Code / Bibtex

This paper introduces a novel contour-based approach named deep snake for real-time instance segmentation.

Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
Junting DongWen JiangQixing HuangHujun BaoXiaowei Zhou
CVPR, 2019  
Project page / Arxiv / Supplement / Video / Code / Bibtex

This paper addresses the problem of 3D pose estimation for multiple people in a few calibrated camera views.

Miscellaneous
Reviewer
CVPR2022-2023, ICCV2023, ECCV 2022, T-PAMI, 3DV 2022

Teaching Assistant
CIS 580: Machine Perception
CIS 680: Advanced Topics in Machine Perception


This guy has an awesome website