Jing Yang

Ph.D. candidate @USC_ICT
Working on: Relighting, Material Acquisition/Generation
now: @nvidia
ex: @TikTok_US @GoogleOSS @dolby
build: @papercopilot

[Jing Yang @jingyangcarl]

@henryzhongsc @thoughts_junk @BlancheMinerva @papercopilot

[Jing Yang @jingyangcarl]

@henryzhongsc @thoughts_junk @BlancheMinerva Paper Copilot score for ICLR is updated in a daily manner.

[Matthias Niessner @MattNiessner]

The hot topic at #ICCV2025 was World Models.

They come in different flavors — (interactive) video models, neural simulators, reconstruction models, etc. — but the overarching goal is clear: Generative AI that predict and simulate how the real world works.

[Chen Guo @ChenGuo96]

🚀 This year, we upgrade Vid2Avatar (#CVPR2023) to 𝗩𝗶𝗱𝟮𝗔𝘃𝗮𝘁𝗮𝗿-𝗣𝗿𝗼 — a method for creating photorealistic, drivable human avatars from monocular videos in the wild, by leveraging a universal prior.
👉 “Pro” stands for Prior.
📢 Vid2Avatar-Pro is accepted to #CVPR2025!

[AK @_akhaliq]

NormalCrafter just dropped on Hugging Face

Learning Temporally Consistent Normals from Video Diffusion Priors

[Radiance Fields @RadianceFields]

Over the next 30 seconds, you'll see more than 300K images of me, making 60 gaussian splats every second.

Last year, I got to visit @8Infinite8.

We are open sourcing all 300K images, in addition to releasing 1800 trained plys for people to download. We are also releasing a free VR experience through @unity through @aras_p plugin.

Check out the higher quality video (there's also a BTS):
https://t.co/UZHVAc3YmO

[Unitree @UnitreeRobotics]

Kungfu BOT: Unitree G1🥳
We have continued to upgrade the Unitree G1's algorithm, enabling it to learn and perform virtually any movement. What other moves would you like to see. Do share with us in the comments. (Please keep a safe distance from the robot.)
#Unitree #Kungfu #EmbodiedAI #SpringFestivalGalaRobot #AI #Humanoid #Bipedal #WorldModel #Dance

[Andrea Tagliasacchi @taiyasaki]

📢📢📢 "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing", a mesh-based 3D represention.

https://t.co/wcI6Xj6UHR
https://t.co/JOzRTfkgbl

Co-lead by my PhD students Shrisudhan Govindarajan and Daniel Rebain, and w/ @kwangmoo_yi

[#CVPR2026 @CVPR]

#CVPR2025 received just over 13,000 submissions – up by about 13% from #CVPR2024.

[Freya Holmér @FreyaHolmer]

oh boy

[Jing Yang @jingyangcarl]

@yuliangxiu Eccv我发现猛发的人，有人藏名字

[Jing Yang @jingyangcarl]

Maybe a real build? Not just a virtual light stage?

[Jing Yang @jingyangcarl]

Real-time user activity map when reviews are out for @NeurIPSConf #NeurIPS2024

[Jing Yang @jingyangcarl]

Even though the polarized reflectance field didn’t make it into #ECCV2024 @eccvconf, I'd like to showcase more scanned objects using Light Stage at @USC_ICT @USCViterbi @USC.
Check out examples of decomposed materials on this page: https://t.co/xeOZGrAsHT

[Jing Yang @jingyangcarl]

Just developed a web virtual Light Stage demo enabling an OLAT simulation using @threejs. Improve later for more features.

Site: https://t.co/L8UHap1FfE
Code: https://t.co/8zNaRiPGn7

[Jing Yang @jingyangcarl]

Some examples of the polarized reflectance field database I developed last year using Light Stage with RED KOMODO Cameras enabling a cleaner separation of diffuse and specular reflection. @USC_ICT

[Jing Yang @jingyangcarl]

@sunjiao123sun_ Congrats!!!!!!

[Jing Yang @jingyangcarl]

@NaveenManwani17 @CVPR @yuming_gu

[Jing Yang @jingyangcarl]

@AmieCS @CVPR Thanks for the notification. It's quite hard to automatically cluster them together. I also tried llm, but the results are still not very much guaranteed. Maybe build a dictionary or something in the future to make it more accurate.

[Jing Yang @jingyangcarl]

Check out which affiliation has the most CVPR papers! 📚✨🏆 @CVPR #CVPR2024

https://t.co/6vAgM3TMWh

[Jing Yang @jingyangcarl]

@jbhuang0604 OMG, thanks for the comments on my project!! I followed you for a while!!