Ting-Chun Wang

Fantastic work done by our intern @YuYingYeh1

We extend our approach to portrait video relighting. We show that videos relit by our framework contain much less flickering and look temporally smoother than existing video relighting approaches.

Check out Lumos: our new portrait relighting framework for SIGGRAPH Asia 2022! Paper: arxiv.org/abs/2209.10510 Project: deepimagination.cc/Lumos Demo: imaginaire.cc/Lumos/ @luminohope @sameh_khamis @jankautz @liu_mingyu

Check out our new work on face-vid2vid, a neural talking-head model for video conferencing that is 10x more bandwidth efficient than H264, while also able to achieve face redirection project nvlabs.github.io/face-vid2vid/ video youtu.be/nLYg9Waw72U @arunmallya @liu_mingyu #GAN

Check out our new work on face-vid2vid, a neural talking-head model for video conferencing that is 10x more bandwidth efficient than H264 arxiv arxiv.org/abs/2011.15126 project nvlabs.github.io/face-vid2vid/ video youtu.be/nLYg9Waw72U @tcwang0509 @arunmallya #GAN

An update to #Imaginaire The pretrained world-consistent vid2vid (nvlabs.github.io/wc-vid2vid/) model for the MannequinChallenge dataset has been released! Code and a lot of other models at: github.com/NVlabs/imagina… By @liu_mingyu @tcwang0509 @xunhuang1995

If this works, it’s just nuts. Nvidia has come up with a video compression algorithm that lets you do Zoom calls with a tiny fraction of the bandwidth usually required. Could be a game-changer for people with poor internet connections. youtube.com/watch?v=NqmMnj… (Via @chrismessina!)

Introducing #Imaginaire a #PyTorch library with optimized implementations of several #GAN image and video synthesis methods developed at #NVIDIA code github.com/NVlabs/imagina… video youtu.be/jgTX5OnAsYQ By @liu_mingyu @tcwang0509 @arunmallya @xunhuang1995

Introducing #Imaginaire a #PyTorch library with optimized implementations of several #GAN image and video synthesis methods developed at #NVIDIA code github.com/NVlabs/imagina… video youtu.be/jgTX5OnAsYQ

Excited to share our #ECCV2020 paper on world-consistent #vid2vid. Compared to vid2vid, our new framework can render consistent views of the virtual 3D world. @NVIDIAAI #GAN with @arunmallya Karan Sapra @liu_mingyu project: nvlabs.github.io/wc-vid2vid/ video: youtu.be/rlCh6-2NfSg

1/4 Exciting to share our #ECCV2020 paper on world-consistent #vid2vid on generating consistent renderings of 3D world. @NVIDIAAI #GAN with @arunmallya @tcwang0509 Karan Sapra paper tinyurl.com/y45xxej6 project nvlabs.github.io/wc-vid2vid/ video youtu.be/rlCh6-2NfSg

Join us tomorrow (Sunday June 14th) for our #CVPR2020 tutorial on novel view synthesis. We'll be streaming all of it live! youtu.be/OEUHalxanuc Stream start at 9:15am PDT Info nvlabs.github.io/nvs-tutorial-c…

Glad to share our #NeurIPS2019 paper on few-shot vid2vid where we address the scalability issue of our #vid2vid. Now, with 1model and as few as 1 example image provided in the test time, we could render the motion of a target subject. nvlabs.github.io/few-shot-vid2v… code coming soon.

So happy to share the news that @NVIDIADesign #GauGAN won both best real time live demo award and people’s choice of best demo award in #SIGGRAPH2019 Real-Time Live. @junyanz89 @gavriilklimov @tcwang0509 @chrisjhebert Special thank to @goodfellow_ian to bring #GAN to this world.

In CVPR2019, the #StyleGAN paper won the best paper honorable mention and #SPADE/#GauGAN paper won the best paper finalist. Congratulates to all the GAN authors! @nvidia

We are running a tutorial on deep learning for content creation in CVPR on Sunday nvlabs.github.io/dl-for-content…. We have a set of amazing speakers including @phillip_isola @jtompkin Tero Kerras, @FidlerSanja Sylvain Paris @tcwang0509 @junyanz89 @elishechtman Please come to join us.

The #GauGAN beta version is now available to everyone as a web service via nvda.ws/2WsY2cM #NVIDIA AI Playground A short illustration video is available in bit.ly/2XIgTSr May everybody have fun with the app. #GAN, #SPADE

Check out our #CVPR19 oral paper on a new conditional normalization layer for semantic image synthesis #SPADE and its demo app #GauGAN paper bit.ly/nvspade website bit.ly/wwwspade video1 bit.ly/2HEvOrD @tcwang0509 @junyanz89