Frank Zhiyang Dou
@frankzydou.bsky.social
MPhil in Computer Graphics @HKU. Visiting @Penn.
CharacterAnimation&Geometry&Topology&Physics-based Animation&Simulation&AIGC.
Homepage: frank-zy-dou.github.io
I doubt existence.
CharacterAnimation&Geometry&Topology&Physics-based Animation&Simulation&AIGC.
Homepage: frank-zy-dou.github.io
I doubt existence.
Submitting a paper is just a snapshot of ongoing work. The final stretch often uncovers overlooked details, and true clarity usually comes after the deadline—making post-deadline improvements even more efficient. But before that, don’t forget to enjoy a well-earned rest! 😄
May 31, 2025 at 4:27 AM
Submitting a paper is just a snapshot of ongoing work. The final stretch often uncovers overlooked details, and true clarity usually comes after the deadline—making post-deadline improvements even more efficient. But before that, don’t forget to enjoy a well-earned rest! 😄
Hi, 🇸🇬! At #ICLR2025, I’ll be presenting our work 🎲DICE!
With DICE, one can explore hand-face interactions 📷 — this feedforward method simultaneously estimates hand and face poses, contact points, and deformations from a single image.
📍 Hall 3+Hall 2B #130 Poster Session 6
🕒 Sat 26 Apr, 3–5:30 p.m.
With DICE, one can explore hand-face interactions 📷 — this feedforward method simultaneously estimates hand and face poses, contact points, and deformations from a single image.
📍 Hall 3+Hall 2B #130 Poster Session 6
🕒 Sat 26 Apr, 3–5:30 p.m.
April 23, 2025 at 2:43 PM
Hi, 🇸🇬! At #ICLR2025, I’ll be presenting our work 🎲DICE!
With DICE, one can explore hand-face interactions 📷 — this feedforward method simultaneously estimates hand and face poses, contact points, and deformations from a single image.
📍 Hall 3+Hall 2B #130 Poster Session 6
🕒 Sat 26 Apr, 3–5:30 p.m.
With DICE, one can explore hand-face interactions 📷 — this feedforward method simultaneously estimates hand and face poses, contact points, and deformations from a single image.
📍 Hall 3+Hall 2B #130 Poster Session 6
🕒 Sat 26 Apr, 3–5:30 p.m.
Reposted by Frank Zhiyang Dou
Can Video Diffusion Model Reconstruct 4D Geometry?
Jinjie Mai, Wenxuan Zhu, Haozhe Liu, Bing Li, Cheng Zheng, Jürgen Schmidhuber, Bernard Ghanem
tl;dr: pretrained video VAE->finetune pointmap VAE; finetune Open-Sora within latent space of video&pointmap
arxiv.org/abs/2503.21082
Jinjie Mai, Wenxuan Zhu, Haozhe Liu, Bing Li, Cheng Zheng, Jürgen Schmidhuber, Bernard Ghanem
tl;dr: pretrained video VAE->finetune pointmap VAE; finetune Open-Sora within latent space of video&pointmap
arxiv.org/abs/2503.21082
March 28, 2025 at 7:30 AM
Can Video Diffusion Model Reconstruct 4D Geometry?
Jinjie Mai, Wenxuan Zhu, Haozhe Liu, Bing Li, Cheng Zheng, Jürgen Schmidhuber, Bernard Ghanem
tl;dr: pretrained video VAE->finetune pointmap VAE; finetune Open-Sora within latent space of video&pointmap
arxiv.org/abs/2503.21082
Jinjie Mai, Wenxuan Zhu, Haozhe Liu, Bing Li, Cheng Zheng, Jürgen Schmidhuber, Bernard Ghanem
tl;dr: pretrained video VAE->finetune pointmap VAE; finetune Open-Sora within latent space of video&pointmap
arxiv.org/abs/2503.21082
Reposted by Frank Zhiyang Dou
The AI for Content Creation workshop #CVPR2025 is accepting paper submissions. ai4cc.net Deadline March 21st 2025 midnight PST. 4 page extended abstracts, 8 pagers, and previously published work (ECCV, NeurIPS, even CVPR)! Many topics 📷📹🎬🎲✒️📃🖼️👗👔🏢 - come spend the day with us!
AI4CC 2025
ai4cc.net
March 14, 2025 at 4:02 PM
Reposted by Frank Zhiyang Dou
Hmmmmm...... I like it black
March 16, 2025 at 4:50 PM
Hmmmmm...... I like it black
Reposted by Frank Zhiyang Dou
Libraries and museums are integral to scientific advancement and to our core mission of #scienceforall. Stand Up for Science stands with @amlibraryassoc.bsky.social!
Please call your representatives and let them know you STRONGLY oppose this attack on access to knowledge.
#standupforscience
Please call your representatives and let them know you STRONGLY oppose this attack on access to knowledge.
#standupforscience
President Trump's executive order to eliminate the Institute of Museum & Library Services would have disastrous effects for communities nationwide. We call on all Americans who value reading & learning to reach out to their elected leaders.
Read ALA's full response: www.ala.org/news/2025/03...
Read ALA's full response: www.ala.org/news/2025/03...
March 16, 2025 at 12:13 PM
Libraries and museums are integral to scientific advancement and to our core mission of #scienceforall. Stand Up for Science stands with @amlibraryassoc.bsky.social!
Please call your representatives and let them know you STRONGLY oppose this attack on access to knowledge.
#standupforscience
Please call your representatives and let them know you STRONGLY oppose this attack on access to knowledge.
#standupforscience
Reposted by Frank Zhiyang Dou
If you are aware of grad program reduction due to cuts in science funding in the USA -- please help catalog it! docs.google.com/forms/d/e/1F... 🧪🌿🐸
Grad Admissions Impact Survey
It is grad admissions season and many postbacs are feeling the chilling impacts of the Trump administration's recent executive orders freezing and slashing research funding. Dozens of graduate program...
docs.google.com
March 17, 2025 at 12:48 AM
If you are aware of grad program reduction due to cuts in science funding in the USA -- please help catalog it! docs.google.com/forms/d/e/1F... 🧪🌿🐸
Reposted by Frank Zhiyang Dou
Reposted by Frank Zhiyang Dou
The submission deadline for the 4D Vision Workshop is in two weeks on March 28.
Both 4-page and 8-page submissions are welcome. Check the website for more detail: 4dvisionworkshop.github.io
Hope to see many of you at CVPR! @cvprconference.bsky.social
Both 4-page and 8-page submissions are welcome. Check the website for more detail: 4dvisionworkshop.github.io
Hope to see many of you at CVPR! @cvprconference.bsky.social
March 14, 2025 at 2:33 PM
The submission deadline for the 4D Vision Workshop is in two weeks on March 28.
Both 4-page and 8-page submissions are welcome. Check the website for more detail: 4dvisionworkshop.github.io
Hope to see many of you at CVPR! @cvprconference.bsky.social
Both 4-page and 8-page submissions are welcome. Check the website for more detail: 4dvisionworkshop.github.io
Hope to see many of you at CVPR! @cvprconference.bsky.social
Reposted by Frank Zhiyang Dou
#CVPR2025 Area Chairs (ACs) identified a number of highly irresponsible reviewers, those who either abandoned the review process entirely or submitted egregiously low-quality reviews, including some generated by large language models (LLMs).
1/2
1/2
February 28, 2025 at 1:44 AM
#CVPR2025 Area Chairs (ACs) identified a number of highly irresponsible reviewers, those who either abandoned the review process entirely or submitted egregiously low-quality reviews, including some generated by large language models (LLMs).
1/2
1/2
Reposted by Frank Zhiyang Dou
Applications due in less than a week!
Announcing SGI 2025! Undergrads and MS students: Apply for 6 weeks of paid summer geometry processing research. No experience needed: 1 week tutorials + 5 weeks of projects. Mentors are top researchers in this emerging branch of graphics/computing/math. sgi.mit.edu
February 11, 2025 at 3:45 PM
Applications due in less than a week!
Reposted by Frank Zhiyang Dou
Excited to bring the 5th CV4Animals Workshop to #CVPR2025
We welcome submissions in 2 tracks:
1) unpublished work up to 4 pages
2) papers published within last 2 years
Submit by Mar 28 & join us with amazing speakers in Nashville:
www.cv4animals.com
🦒🪼🐬🐿️🦩🐢🦘🦜🦥🦋
@cvprconference.bsky.social
We welcome submissions in 2 tracks:
1) unpublished work up to 4 pages
2) papers published within last 2 years
Submit by Mar 28 & join us with amazing speakers in Nashville:
www.cv4animals.com
🦒🪼🐬🐿️🦩🐢🦘🦜🦥🦋
@cvprconference.bsky.social
February 1, 2025 at 4:25 AM
Excited to bring the 5th CV4Animals Workshop to #CVPR2025
We welcome submissions in 2 tracks:
1) unpublished work up to 4 pages
2) papers published within last 2 years
Submit by Mar 28 & join us with amazing speakers in Nashville:
www.cv4animals.com
🦒🪼🐬🐿️🦩🐢🦘🦜🦥🦋
@cvprconference.bsky.social
We welcome submissions in 2 tracks:
1) unpublished work up to 4 pages
2) papers published within last 2 years
Submit by Mar 28 & join us with amazing speakers in Nashville:
www.cv4animals.com
🦒🪼🐬🐿️🦩🐢🦘🦜🦥🦋
@cvprconference.bsky.social
DICE 🎲was accepted by #ICLR2025.
With DICE, one can learn more about hand-face interactions 👤👋. This end-to-end method also enables better scalability to learn and model hand-face interaction. Congrats to our amazing intern Peter QingXuan Wu!
Project page: frank-zy-dou.github.io/projects/DIC...
With DICE, one can learn more about hand-face interactions 👤👋. This end-to-end method also enables better scalability to learn and model hand-face interaction. Congrats to our amazing intern Peter QingXuan Wu!
Project page: frank-zy-dou.github.io/projects/DIC...
January 27, 2025 at 12:28 AM
DICE 🎲was accepted by #ICLR2025.
With DICE, one can learn more about hand-face interactions 👤👋. This end-to-end method also enables better scalability to learn and model hand-face interaction. Congrats to our amazing intern Peter QingXuan Wu!
Project page: frank-zy-dou.github.io/projects/DIC...
With DICE, one can learn more about hand-face interactions 👤👋. This end-to-end method also enables better scalability to learn and model hand-face interaction. Congrats to our amazing intern Peter QingXuan Wu!
Project page: frank-zy-dou.github.io/projects/DIC...
Reposted by Frank Zhiyang Dou
Reposted by Frank Zhiyang Dou
Reposted by Frank Zhiyang Dou
I think a lot of technical people (me included) always felt this was the case, that ML image generation approaches, untethered from some interpretable, controllable model of the world (like a game engine) would never work. It's cool to see that Jensen agrees.
www.pcworld.com/article/2570...
www.pcworld.com/article/2570...
Nvidia CEO: PC games will never be entirely rendered by AI
A day after launching the GeForce 50-series family of GPUs, Nvidia chief executive Jensen Huang was asked about whether AI would take over the entire 3D rendering process.
www.pcworld.com
January 8, 2025 at 7:57 PM
I think a lot of technical people (me included) always felt this was the case, that ML image generation approaches, untethered from some interpretable, controllable model of the world (like a game engine) would never work. It's cool to see that Jensen agrees.
www.pcworld.com/article/2570...
www.pcworld.com/article/2570...
Genesis has now released an official speed benchmarking report, community channels, and a new version 0.2.1, which features faster kernel loading, smoke simulation, more RL training modules, etc.
github.com/zhouxian/gen...
#Genesis #Robotics #Simulation
github.com/zhouxian/gen...
#Genesis #Robotics #Simulation
GitHub - zhouxian/genesis-speed-benchmark
Contribute to zhouxian/genesis-speed-benchmark development by creating an account on GitHub.
github.com
January 8, 2025 at 7:22 PM
Genesis has now released an official speed benchmarking report, community channels, and a new version 0.2.1, which features faster kernel loading, smoke simulation, more RL training modules, etc.
github.com/zhouxian/gen...
#Genesis #Robotics #Simulation
github.com/zhouxian/gen...
#Genesis #Robotics #Simulation
🚀 ProTracker delivers accurate and robust Tracking Any Point (TAP) with a Kalman filter-inspired Probabilistic approach, seamlessly fusing optical flow and semantic cues for smoother, more accurate trajectories!
Project page: michaelszj.github.io/protracker/
Paper: arxiv.org/abs/2501.03220
Project page: michaelszj.github.io/protracker/
Paper: arxiv.org/abs/2501.03220
January 8, 2025 at 12:57 AM
🚀 ProTracker delivers accurate and robust Tracking Any Point (TAP) with a Kalman filter-inspired Probabilistic approach, seamlessly fusing optical flow and semantic cues for smoother, more accurate trajectories!
Project page: michaelszj.github.io/protracker/
Paper: arxiv.org/abs/2501.03220
Project page: michaelszj.github.io/protracker/
Paper: arxiv.org/abs/2501.03220
Reposted by Frank Zhiyang Dou
ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking
Tingyang Zhang, @cwchenwang.bsky.social, @frankzydou.bsky.social, Qingzhe Gao, Jiahui Lei, Baoquan Chen, @lingjieliu.bsky.social
arxiv.org/abs/2501.03220
Tingyang Zhang, @cwchenwang.bsky.social, @frankzydou.bsky.social, Qingzhe Gao, Jiahui Lei, Baoquan Chen, @lingjieliu.bsky.social
arxiv.org/abs/2501.03220
January 7, 2025 at 4:30 AM
ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking
Tingyang Zhang, @cwchenwang.bsky.social, @frankzydou.bsky.social, Qingzhe Gao, Jiahui Lei, Baoquan Chen, @lingjieliu.bsky.social
arxiv.org/abs/2501.03220
Tingyang Zhang, @cwchenwang.bsky.social, @frankzydou.bsky.social, Qingzhe Gao, Jiahui Lei, Baoquan Chen, @lingjieliu.bsky.social
arxiv.org/abs/2501.03220
Reposted by Frank Zhiyang Dou
Announcing SGI 2025! Undergrads and MS students: Apply for 6 weeks of paid summer geometry processing research. No experience needed: 1 week tutorials + 5 weeks of projects. Mentors are top researchers in this emerging branch of graphics/computing/math. sgi.mit.edu
January 6, 2025 at 3:48 PM
Announcing SGI 2025! Undergrads and MS students: Apply for 6 weeks of paid summer geometry processing research. No experience needed: 1 week tutorials + 5 weeks of projects. Mentors are top researchers in this emerging branch of graphics/computing/math. sgi.mit.edu
🔥DON’T MISS IT! GENESIS is here!
🔥Genesis is a highly efficient, user-friendly, and versatile simulation platform with comprehensive functionality.
Github: github.com/Genesis-Embo...
Project Page: genesis-embodied-ai.github.io
Very happy to be part of this amazing work!
x.com/zhou_xian_/s...
🔥Genesis is a highly efficient, user-friendly, and versatile simulation platform with comprehensive functionality.
Github: github.com/Genesis-Embo...
Project Page: genesis-embodied-ai.github.io
Very happy to be part of this amazing work!
x.com/zhou_xian_/s...
GitHub - Genesis-Embodied-AI/Genesis: A generative world for general-purpose robotics & embodied AI learning.
A generative world for general-purpose robotics & embodied AI learning. - Genesis-Embodied-AI/Genesis
github.com
December 18, 2024 at 11:15 PM
🔥DON’T MISS IT! GENESIS is here!
🔥Genesis is a highly efficient, user-friendly, and versatile simulation platform with comprehensive functionality.
Github: github.com/Genesis-Embo...
Project Page: genesis-embodied-ai.github.io
Very happy to be part of this amazing work!
x.com/zhou_xian_/s...
🔥Genesis is a highly efficient, user-friendly, and versatile simulation platform with comprehensive functionality.
Github: github.com/Genesis-Embo...
Project Page: genesis-embodied-ai.github.io
Very happy to be part of this amazing work!
x.com/zhou_xian_/s...
Reposted by Frank Zhiyang Dou
Spotted this in the wild. I know it kinda doesn't make sense, but CVPR 2025 submissions can't be publicly stated as such on arxiv or on your personal website. If you wrote "in submission to CVPR 2025" somewhere on the open internet, you should delete it ASAP.
December 18, 2024 at 2:26 AM
Spotted this in the wild. I know it kinda doesn't make sense, but CVPR 2025 submissions can't be publicly stated as such on arxiv or on your personal website. If you wrote "in submission to CVPR 2025" somewhere on the open internet, you should delete it ASAP.
Reposted by Frank Zhiyang Dou
As my kids are singing APT non-stop these days, I did a bit of reverse engineering of the APT music video and tried to understand why the MV is so addictive.
Here is what I learned.
Here is what I learned.
December 17, 2024 at 9:53 PM
As my kids are singing APT non-stop these days, I did a bit of reverse engineering of the APT music video and tried to understand why the MV is so addictive.
Here is what I learned.
Here is what I learned.