At CVPR, you can skip our paper—but don't skip our concert! Join us at the CVPR Music Reception!
📍 Colorado Convention Center, Bluebird Ballroom on the Fifth floor.
🕖 Saturday, 7:00 PM
Opening Band setlist:
🎮 Expedition 33 OST
🎤 Time to Say Goodbye
🏴☠️ He's a Pirate
and more.
Papers will still be online. The concert won't. ♪♫♬
A sneak peek from our rehearsal for the CVPR Music Reception! 🎵
#CVPR #CVPR2026
LCA is accepted at CVPR 2026! 🚀
We introduce a pre/post-training paradigm for 3D avatars (1M in-the-wild videos ➡️ studio data).
The result? High-fidelity full-body avatars with emergent relightability and zero-shot stylization.
Project: https://t.co/liddQrFIqF
#CVPR2026
Excited to share our #ICCV25 paper presenting an Augmented Mass-Spring (AMS) model for real-time dense #HairSimulation!
AMS adds biphasic coupling to traditional mass-spring systems → better stability, global preservation and non-Hookean effects — efficiently.
@KAUST_News@Adobe
📢 #SIGGRAPH2025 I'll be presenting our paper "3DGH: 3D Head Generation with Composable Hair and Face". Swing by and let's talk about hair and head generation! #Meta#Yale
⏰ Monday, Aug 11 | 2:00pm - 3:30pm PDT
📍 West Building, Rooms 301-305
🔗 https://t.co/PFhQbd4vIK
Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers!
https://t.co/z8w4YJKTep
📢 #ICLR2025 I'll be presenting our spotlight paper "Perm: A Parametric Representation for Multi-Style 3D Hair Modeling". Swing by and let's talk about hair! #Adobe#AdobeResearch#Yale
⏰ Friday, April 25 | 10am - 12:30pm SGT
📍 Hall 3 | Poster #90
🔗 https://t.co/VNgZEzfVDR
Here’s our state-of-the-art hair simulator in action! It seamlessly handles complex hair-object interactions in real time, ensuring stability and enhanced realism. 💈✨
Want to give it a try? It’s open source! 🎉 Dive in: https://t.co/ul80Oer2dO
#HairSimulation#DigitalHair
Looking for the perfect hairstyle for the upcoming holidays?🎄✨ Join us this Friday at Real-Time Live! for our demo Digital Salon, an interactive hair grooming and simulation tool (Friday 4pm, Hall C 4F). Swing by if you’re interested! #SIGGRAPHAsia2024#AdobeResearch#Adobe
🎥 Watch the Real-Time Live! trailer for an exclusive look at the most cutting-edge real-time graphics hitting the stage at SIGGRAPH Asia 2024! Witness live demos that redefine innovation.
Real-Time Live! Chair: Takahito Tejima (@gishicho)
🎟️https://t.co/D4oyQNiq7c
#CG#Tech
🚀 Debut "Digital Salon: An AI and Physics-Driven Tool for 3D Hair Grooming and Simulation"! Generate detailed hairstyles, combine text-based creation, interactive editing, and AI rendering—all in one. With real-time simulation of 10,000 to 80,000 strands on an NVIDIA Laptop GPU, Digital Salon streamlines advanced hair design for everyone. Explore it here: https://t.co/uiFKylguQZ #AI #3DModeling #HairSimulation #DigitalArt #DigitalHuman #Adobe #NVIDIA
How can Wukong's hair not be majestic? Check Digital Salon ! An all-in-one toolkit with AI hairstyle generation and real-time physics simulation for tens of thousands of strands, all running on a laptop. Game devs, what are you waiting for? To lead the future of AAA titles, real-time hair simulation is a must!"https://t.co/YbINAucTg8 #AI #3DModeling #HairSimulation #GameDev #AAA #DigitalArt
🚀 Debut "Digital Salon: An AI and Physics-Driven Tool for 3D Hair Grooming and Simulation"! Generate detailed hairstyles, combine text-based creation, interactive editing, and AI rendering—all in one. With real-time simulation of 10,000 to 80,000 strands on an NVIDIA Laptop GPU, Digital Salon streamlines advanced hair design for everyone. Explore it here: https://t.co/uiFKylguQZ #AI #3DModeling #HairSimulation #DigitalArt #DigitalHuman #Adobe #NVIDIA
@Michael_J_Black@Papagina_Yi 3. Anyway our code and data are released. We welcome people to test them and propose more mathematically-sound reasons than our simple suspects! (3/3)
@Michael_J_Black@Papagina_Yi 2. There is actually a tiny difference between the variance explained by 20 and 64 PCs (99.98% vs 99.99%). Our suspect is: though high-frequency features are sparse and contribute little to the variance, they are important to generalize fitted PCs to unseen curlier data. (2/3)
Sharing "Perm: A Parametric Representation for Multi-Style 3D Hair Modeling"! Aiming to be the SMPL for 3D hair, it has disentangled parameters to control hair cut types and curl patterns, a generic prior for single-view reconstruction and hair-conditioned image generation. We've released the code, the trained model on 20k public hair data, and by popular demand, the data itself! https://t.co/4JERcfUhqJ #AdobeFirefly #3DModeling #DigitalHair
Adobe researchers are presenting new work at this year's Neural Information Processing Systems conference (#NeurIPS2022). Check out the list of accepted papers and other contributions from @Adobe! https://t.co/B1nzSTZm8C
Have you wondered how to incorporate implicit neural representations with motion modeling? Check out our spotlight paper "NeMF: NeMF: Neural Motion Fields for Kinematic Animation" (https://t.co/gHarVLL1Ya) at #NeurIPS2022! Poster session: 12/1 12:30 p.m. EST - 2 p.m. EST (1/5)
The technology in NeMF is also involved in the super cool #ProjectMotionMix at #AdobeMax 2022 to generate seamless looping motions! Check out the video here (https://t.co/F046u0pbFf). (4/5)