Ruihang Zhang

Introducing 📢📢ProxyPose📢📢 ✨Track 6-DoF motion of any query pixel via video-to-video translation 📰ArXiv: arxiv.org/abs/2607.06555 💻Code: github.com/ruihangzhang97… 🌐Webpage: ruihangzhang97.github.io/proxypose

[4/4] Shoutout to the amazing team: @taubnerfelix , @pooja_ravioli, @kyroskutulakos, and @DaveLindell!

[3/4] 🚀Despite training only on synthetic data, ProxyPose outperforms previous work, especially on challenging cases like occlusion, reflective or transparent objects, textureless surfaces, and non-rigid motion—scenarios where many existing methods struggle.

Introducing 📢📢ProxyPose📢📢 ✨Track 6-DoF motion of any query pixel via video-to-video translation 📰ArXiv: arxiv.org/abs/2607.06555 💻Code: github.com/ruihangzhang97… 🌐Webpage: ruihangzhang97.github.io/proxypose

@maxwell54650346 🔥

I recently had the chance to live demo my previous internship project RefVFX to Jensen Huang (and CMU SCS Dean Martial Herbert) around the time of CMU commencement this year! I finally got around to open sourcing the dataset and inference code, so feel free to check it out! [1/3]

@HaojunQiu congrats @HaojunQiu!! amazing work!!

📢📢📢We introduce Efficient-SID⚡️: training-free single-image diffusion model that generates images by sampling directly from an input image's patch distribution. Our method enables megapixel generation in <1s and scales to gigapixel generation. We also enable stylization, editing, and other applications. The outputs are constrained to follow exactly the patch distribution of the input — something that is very difficult to do with large models! #CVPR2026 Highlight 🌐 haojunqiu.github.io/efficient-SID/ 📄 arxiv.org/abs/2606.04299 [1/6]

@yusuf_dalva wow big dawg 🫵

Thrilled to announce that Canvas-to-Image (C2I) is accepted to #SIGGRAPH2026! 🎥 We simplify complex generation into one intuitive interface. Control ID, Pose, and Boxes: all from a single canvas. You are the designer. Kudos to the team: @guocheng_qian, Maya Goldenberg, @tsaishien_chen, @AbermanKfir, @SergeyTulyakov, @PINguAR and @kcjacksonwang! See you in LA!