
Research Scientist @Meta Reality Labs | Previously @virginia_tech @UMich @OregonState | Rubik's Cube, tennis, painting, national parks.
Seattle, USA
Joined August 2013
- Tweets24
- Following237
- Followers473
- Likes291
Here is a screen recording of the real-time demo in Quest 3. We are working on the ultra-high-quality 360 reconstruction of dynamic scenes for a fully immersive demo. Stay tuned!
This dataset is collected during our summer hikes. You should join us if you are also into outdoor activities!
Progressively Optimized Local Radiance Fields for Robust View Synthesis
abs: arxiv.org/abs/2303.13791
project page: localrf.github.io/
What a journey! Thank you @jbhuang0604, for all your support and help along the way! Could not have done it without your support! Also, I am very fortunate to have these awesome committee members.
Next stop: I'll be joining @JPKopf's team at Meta as a Research Scientist!
Congrats Chen Gao (@gaochen315) for passing the PhD defense!! 🥳
Special thanks to committee (Lynn, @berty38, @JPKopf, Harpreet)!
Chen’s PhD made solid contributions to computational photography/videography. Follow his work!
chengao.vision
Great results! Maybe extend the idea to the 3D space as well?
Always a great fun when Two Minute Papers covers your work! w/ @yoni_kasten @dolevofri @oliverwang81
1
3
As a gift for Christmas, we have released the code for our dynamic view synthesis paper
github.com/gaochen315/Dynami…
Have fun!
SUPER excited to share our work Dynamic View Synthesis from Dynamic Monocular Video! Check out our fun teaser video 😎!
Paper: arxiv.org/abs/2105.06468
Project: free-view-video.github.io/
w/ @gaochen315, @ayush29feb, @JPKopf
Chen Gao 髙諶 retweeted
Omnimatte: Associating Objects and Their Effects in Video
pdf: arxiv.org/pdf/2105.06993.pdf
abs: arxiv.org/abs/2105.06993
project page: omnimatte.github.io/
Chen Gao 髙諶 retweeted
Want to improve the data efficiency of your semantic segmentation model?
Check our recent #ICLR2021 paper "PseudoSeg: Designing Pseudo Labels for Semantic Segmentation"!
Code: github.com/googleinterns/wss
Project: yuliang.vision/pseudo_seg/
See you on 3rd May 5-7 pm PDT/ 8-10pm EDT!
The Google Colab of our video completion is up! Now you can edit the video (e.g. removing objects, FOV extrapolation) with one click!
colab.research.google.com/dr…
Thanks @twominutepapers for covering our work!
Project: chengao.vision/FGVC/
Code: github.com/vt-vl-lab/FGVC
This quoted post is unavailable.
Hooray! The code is up! Have fun!
github.com/vt-vl-lab/FGVC
w/ Ayush, Jia-Bin (@jbhuang0604), and Johannes (@JPKopf)
Chen Gao 髙諶 retweeted
Layered Neural Rendering for Retiming People in Video
pdf: arxiv.org/pdf/2009.07833.pdf
abs: arxiv.org/abs/2009.07833
project page: retiming.github.io/
Chen Gao 髙諶 retweeted
WOW, this demo is soooo impressive! Congrats to @gaochen315, @jbhuang0604 and their collaborators!
Super excited to share our work on video completion at #ECCV2020!🤩Our method seamlessly removes objects, watermarks, or expands field-of-view from casually captured videos.
Paper: arxiv.org/abs/2009.01835
Project: chengao.vision/FGVC/
With @gaochen315, Ayush, and @JPKopf
Super excited to share our work on video completion at #ECCV2020!🤩Our method seamlessly removes objects, watermarks, or expands field-of-view from casually captured videos.
Paper: arxiv.org/abs/2009.01835
Project: chengao.vision/FGVC/
With @gaochen315, Ayush, and @JPKopf
Chen Gao 髙諶 retweeted
Flow-edge Guided Video Completion
pdf: arxiv.org/pdf/2009.01835.pdf
abs: arxiv.org/abs/2009.01835
project page: chengao.vision/FGVC/
webpage: filebox.ece.vt.edu/~chengao/…
Chen Gao 髙諶 retweeted
Jinwoo and @gaochen315 presenting our work on mitigating scene biases in action recognition. #NeurIPS2019 – at Vancouver, British Columbia










