Purvi Goel

So thrilled to share “Generative Motion Infilling From Imprecisely Timed Keyframes”, to be presented at #Eurographics2025 (1/4) Website: purvigoel.github.io/imprecise-timi… Paper: arxiv.org/abs/2503.01016 Video: youtube.com/watch?v=izbbt1…

Had a great time in London at #Eurographics2025 talking about my obsession: keyframe timing. Why its tricky, how it affects animations generated by in-betweening models, and what it means for training more useful models to help you animate :)

Awesome look into the future of humanoid robots and what we can learn from character animation from Karen Liu’s keynote at #Eurographics2025!

🔔Excited to announce that #AnyTop has been accepted to #SIGGRAPH2025!🥳 ✅ A diffusion model that generates motion for arbitrary skeletons ✅ Using only a skeletal structure as input ✅ Learns semantic correspondences across diverse skeletons 🌐 Project: anytop2025.github.io/Anytop-page

🎉 Our paper "PGC: Physics-Based Gaussian Cloth from a Single Pose" has been accepted to #CVPR2025! 👕 PGC uses a PBR + 3DGS representation to render simulation-ready garments under novel lighting and motion, all from a single static frame. ✨Web: phys-gaussian-cloth.github.io 🧵1/4

I'm thrilled to announce that our research paper, "Quaffure: Real-Time Quasi-Static Neural Hair Simulation," has been accepted to #CVPR2025! 🥳 Quaffure introduces a novel neural approach to efficiently simulate hair quasi-statically. tuurstuyck.github.io/quaffure/quaff…

Some thoughts on the difficulty of animation timing, particularly in the context of learned motion inbetweening. medium.com/@goel.purvi/th…

Time to democratize humanoid robots! Introducing ToddlerBot, a low-cost ($6K), open-source humanoid for robotics and AI research. Watch two ToddlerBots seamlessly chain their loco-manipulation skills to collaborate in tidying up after a toy session. toddlerbot.github.io

One of the motivating application of this project was to emulate a "photo album" experience. With VisualComposer, you can create image variations from one image. But it also became a more general tool where you not only can generate image variations, but also compose any visual…

But what if you _really_ like reflections? Local Gaussian Density Mixtures updates lumigraphs by optimizing mixtures of per-view volumes for 🌟maximum shine🌟 #SIGGRAPHAsia2024 xchaowu.github.io/papers/lgdm/in… First author Xiuchao Wu is graduating soon and is looking for a job!

🚀 Research Intern Position at the Personalization Team of Snap! 🚀 I'm looking for motivated PhD students to extend the capabilities of foundation image generation models. Areas of focus include multi-modal prompting, compositional generation, and fast adaptation to individual…

Happy to have shared artistic insights to help bring our new sketch-to-image generation tool to life 🧑‍🎨🎨! Check out our UIST paper (work with @VSarukkai, Lu Yuan, @magrawala, @kayvonf) at miatang13.github.io/BlockAndDetail/. 🦾 Try our live demo (linked in our project page)!

Be sure to try the working demo of our new sketch to image generation tool. The demo code and tutorial video are available from the paper website: miatang13.github.io/BlockAndDetail/

We'll be talking all about this work tomorrow at #SIGGRAPH2024 ! Hope to see you at 10:45AM in the "Character Animation From Data" session 🎉