I will be presenting our work HOI-PAGE at #ICML2026 Stop by our poster and have a chat about human-object interaction and more! 🗓️2:30 PM – 4:15 PM, Wed, Jul 8 📍Poster 1313, HALL A

Angela Dai@adai.bsky.social · 3mo ago

Excited to share HOI-PAGE, to appear at #ICML2026! 🚀 @craigleili.bsky.social generates 4D human-object interactions zero-shot from text A part-affordance graph grounds interactions via LLM+video priors, enabling complex multi-person, multi-object interactions 👉 craigleili.github.io/projects/hoi...

Human-object interaction isn't just global proximity. It's a coordinated engagement between body parts and functional object parts. Check out HOI-PAGE for realistic generation via this explicit part-level reasoning!

Angela Dai@adai.bsky.social · 3mo ago

Excited to share HOI-PAGE, to appear at #ICML2026! 🚀 @craigleili.bsky.social generates 4D human-object interactions zero-shot from text A part-affordance graph grounds interactions via LLM+video priors, enabling complex multi-person, multi-object interactions 👉 craigleili.github.io/projects/hoi...

Super excited to have this paper out! Check out this thread if you are curious about disruptive science and “twin papers” with simultaneously discoveries! 🧪

Munjung Kim@mj-kim.bsky.social · 4mo ago

The Higgs mechanism was proposed in 1964 by three independent teams. But here is the puzzle🤔: the "disruption index" says Higgs's paper is among the least disruptive ever. So what is going on? In our new paper, just out in #ScienceAdvances, we take up this puzzle: doi.org/10.1126/scia... 👇 1/7

Check out Seen2Scene — training generative models on real-world, partial 3D scans made simple. Great work by Quan Meng! 🚀

Angela Dai@adai.bsky.social · 4mo ago

📢Seen2Scene Real-world 3D is incomplete, typically requiring training on synthetic scene data. Quan Meng introduces visibility-guided flow matching, enabling training on real partial scans for scan completion & text-to-3D scene generation! Check it out: quan-meng.github.io/projects/see...

@daidedou.bsky.social will present DiffuMatch at #ICCV2025 in Poster Session 2 this afternoon (Tuesday). Stop by and chat with us about spectral diffusion models! 🗓️ Oct 21st (Tue), 15:00 – 17:00 📍 67, Exhibit Hall I

📢 Excited to share our latest #ICCV2025 work DiffuMatch: learning spectral diffusion priors for robust non-rigid shape matching! (1/n)

🤩 Check out Emery's #ICCV2025 work DiffuMatch, a generalizable non-rigid shape matching approach with learned spectral diffusion priors! A live demo is at 🌐 huggingface.co/spaces/daide...

Diffumatch - a Hugging Face Space by daidedou

Upload two 3D mesh files to find and visualize correspondences between them. Adjust settings to refine the matching process. Get colored mesh previews and a text file with the correspondences.

huggingface.co

📢 Excited to share our latest #ICCV2025 work DiffuMatch: learning spectral diffusion priors for robust non-rigid shape matching! (1/n)

📣Our school @uvadatascience.bsky.social has several faculty position openings for the 2025-2026 hiring cycle. Come join a vibrant and growing academic community to shape the future of data science!🚀 datascience.virginia.edu/faculty-jobs

🚀We have PhD openings in my lab at TU Munich! Explore 3D/4D reconstruction & generation, semantic & functional understanding, and more - at the intersection of graphics, vision, and machine learning. 💼PhDs are 100% E13 positions 👉Apply: 3dunderstanding.org/openings.html or via ELLIS!

Excited to join @uvadatascience.bsky.social as an Assistant Professor! Deeply grateful to my advisors @adai.bsky.social, Maks Ovsjanikov, Hongbo Fu, and Chiew-Lan Tai for their unwavering support. 📣We are recruiting PhD students and postdocs to work on #SpatialAI. Flyer below with details!

Creating high-quality 3D models from just a few sketch strokes🤩 Check out Haoxuan's latest work MeshPad!

Matthias Niessner@niessner.bsky.social · last yr.

📢MeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing📢 Users can interactively design 3D models just from a sketch-based interface - check it out! We break down the design process into addition with an autoregressive generator and deletion operations by a classifier.

Check out our #CVPR2025 papers on articulated mesh generation, 4d shape generation with dictionary neural fields, large-scale 3d scene generation and editing, and 3d editing! Congrats to Daoyi Gao, Xinyi Zhang, Alexey Bokhovkin, Quan Meng, and Ziya Erkoc for their amazing work!

(1/n) 📢📢 𝐍𝐞𝐑𝐒𝐞𝐦𝐛𝐥𝐞 𝐯𝟐 𝐃𝐚𝐭𝐚𝐬𝐞𝐭 𝐑𝐞𝐥𝐞𝐚𝐬𝐞 📢📢 Head captures of 7.1MP from 16 cameras at 73fps: * More recordings (425 people) * Better color calibration * Convenient download scripts github.com/tobias-kirsc...

Excited to bring back the 2nd ScanNet++ Novel View Synthesis and 3D Semantic Understanding Challenge at #CVPR 2025! Submit to our new benchmark, now with over 1000 high-fidelity scans of real-world scenes: kaldir.vc.in.tum.de/scannetpp/ Check it out: kaldir.vc.in.tum.de/scannetpp/cv...

📢 ScanNet++ v2 Benchmark Release! 🏆 Test your state-of-the-art models on: 🔹 Novel View Synthesis 📸➡️🖼️ 🔹 3D Semantic & Instance Segmentation 🤖🔍🕶️ Shoutout to @awhiteguitar.bsky.social & Yueh-Cheng Liu for their incredible work👏 🚀Check it out: kaldir.vc.in.tum.de/scannetpp/

Excited to announce ScanNet++ v2!🎉 @awhiteguitar.bsky.social & Yueh-Cheng Liu have been working tirelessly to bring: 🔹1006 high-fidelity 3D scans 🔹+ DSLR & iPhone captures 🔹+ rich semantics Elevating 3D scene understanding to the next level!🚀 w/ @niessner.bsky.social kaldir.vc.in.tum.de/scannetpp

👉 Check out our latest work MeshArt led by Daoyi Gao MeshArt generates articulated 3D objects with clean, compact geometry that can be animated at different articulation states! A step forward in understanding object functionality and interactions🚀

Angela Dai@adai.bsky.social · 2y ago

📢MeshArt: Generating Articulated Meshes with Structure-guided Transformers Daoyi Gao generates articulated meshes with a hierarchical transformer, modeling articulation-aware structures that guide mesh synthesis. w/ Yawar Siddiqui, Lei Li Project Page: daoyig.github.io/Mesh_Art/