Jiaming Sun

孙佳明
suenjiaming@gmail.com
Founder & CEO, 4DV.ai
B.Eng, Southern University of Science and Technology

At 4DV.ai, we are inventing the next generation of visual media—interactive, volumetric, and truly photoreal. In addition to 4DV.ai, I am also affiliated with the 3D Vision Group at Zhejiang University (ZJU), led by Prof. Xiaowei Zhou. Previously, I have worked at DJI and SenseTime and co-founded IDR. I received my bachelor's degree in 2017 from the department of CSE, SUSTech.

Research Interests

I have a broad interest in the science and engineering aspects of intelligent systems, with a particular focus on 3D Computer Vision and Computer Graphics. I have been working on 3D/4D reconstruction, pose estimation, correspondence estimation and digital humans.

I deeply believe that immersive technologies like VR/AR will be ubiquitous as the next generation of human-machine interfaces and will fundamentally change our lives, similar to touchscreens nowadays. Quoting Steve Jobs' remarks on GUI when he visited Xerox PARC in 1979: "You could argue about the number of years it would take, and you could argue about who would be the winners and the losers, but I don't think you could argue that every computer in the world wouldn't eventually work this way." I'm devoting my career to making this happen a little bit sooner.

Recent News

  • 👏 Three papers accepted to CVPR 2022 and SIGGRAPH 2022. ()
  • 😎 Begin the journey of starting a company. ()
  • ✌️ One paper accepted to ICCV 2021. ()

Publications
show selectedshow all by dateshow all by topic

* denotes equal contribution.
Neural 3D Reconstruction in the Wild
SIGGRAPH 2022 (Conference Proceedings)    
PaperProject PageCode
OnePose: One-Shot Object Pose Estimation without CAD Models
CVPR 2022    
PaperProject PageCode
You Don't Only Look Once: Constructing Spatial-Temporal Memory for Integrated Object Pose Estimation and Tracking
ICCV 2021    
PaperProject PageCode
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
CVPR 2021    
Oral Presentation  Best Paper Candidate  
PaperProject PageCode
LoFTR: Detector-Free Local Feature Matching with Transformers
CVPR 2021    
PaperProject PageCode
Disp R-CNN thumbnail loading...
Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
CVPR 2020, TPAMI 2021    
CVPR PaperTPAMI PaperCode

Collaborators