Itai Lang

📢 Thrilled to present our work Best Segmentation Buddies 🤝 at #CVPR2026 this week! Best Segmentation Buddies is a zero-shot method that matches semantic parts between images in the wild and untextured 3D shapes, even across completely different domains! 🦉✈️ 1/6

@cogentia Hi Lorenz, thanks for your interest in our work! The success rate is based on data we have generated. There is also a perceptual study by human evaluators (see the table below). Happy to know more about the biological application! Please let me know your contact details. Thanks!

@ItaiLang Congrats. Very interesting. Apply this deeper and at scale to a biological context: homology down to the genes. I am interested to collab. Is the success right now qualified by a human neural net/evaluator?

📢 Thrilled to present our work Best Segmentation Buddies 🤝 at #CVPR2026 this week! Best Segmentation Buddies is a zero-shot method that matches semantic parts between images in the wild and untextured 3D shapes, even across completely different domains! 🦉✈️ 1/6

📌 Want to know how we match semantic parts across modalities and domains without any supervision? Come to hear about our Best Segmentation Buddies work TODAY! 👋 🏔 #CVPR2026 🕑 11:45 am – 1:45 pm 📍 ExHall F, poster #584 🌐 threedle.github.io/bsb/

@eb1aexperts Thanks!

@ItaiLang Very interesting research direction. Congratulations on the CVPR presentation.

Very excited to be presenting our highlight paper “Deep Feature Deformation Weights” at #CVPR2026! TLDR: Image features make surprisingly good deformation weights. Our feature distillation is the best in the biz. ExHall A&F 555 Poster Session 4 Website: threedle.github.io/dfd/

The work was done in collaboration with colleagues from the 3DL lab at UChicago, @d_w_lyu, @DecaturDale, and Professor @RanaHanocka. For more details, check out our 🌐 Project page: threedle.github.io/bsb/ 📜 Paper: arxiv.org/pdf/2605.18193 ⚙️ Code: github.com/threedle/bsb 6/6

Our method enables new and exciting applications! 🎉 One such application is image-guided local texturing: click a region in the image, find the corresponding 3D part, and transfer its texture onto the mesh. 5/6

Happy to share that our work "RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes" was accepted to #CVPR2026 (findings). Check out the project page: michaelbaltaxe.github.io/rad/

@omerbenishu Wow, amazing!

🚨 Excited to share our new paper: "PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions"! 🎉 We tackle generating photorealistic 4D interactions by deeply coupling generative human motion diffusion with physical simulation! 🧠💥🧵👇(1/4)

Excited to announce that "Let it Snow!" has been accepted to #CVPR2026!🎉 We present a framework for scene-wide dynamic editing of static 3D Gaussian Splatting scenes with dynamic weather effects. galfiebelman.github.io/let-it-snow/ [1/5]

🚀 LL3M Demo is LIVE! You can now try our research prototype 👉github.com/threedle/ll3m LL3M writes Python code that generates 3D assets in Blender. Share your 3D creations with us. We can’t wait to see what you make!

We’ve been building something we’re 𝑟𝑒𝑎𝑙𝑙𝑦 excited about – LL3M: LLM-powered agents that turn text into editable 3D assets. LL3M models shapes as interpretable Blender code, making geometry, appearance, and style easy to modify. 🔗 threedle.github.io/ll3m 1/

Our work “Geometry in Style” will be presented at #CVPR2025 on Sunday at 4pm in ExHall D, poster 219. Drop by and say hi! Our technique is capable of performing expressive text-driven deformations that preserve the input shape identity. 1/

Congrats Brian and team on the best paper honorable mention at #3dv2025 🥳🎉 Brian (hywkim-brian.github.io/site/) is going to start his PhD next year at Columbia with @sellan_s . Make sure to watch out for their awesome works 📈📈📈

@GalFiebelman Congrats Gal! 🥳

Excited to announce that "4-LEGS: 4D Language Embedded Gaussian Splatting" has been accepted to #Eurographics2025! 🎉 We connect language with a 4D Gaussian Splatting representation to enable spatiotemporal localization using just text prompts! tau-vailab.github.io/4-LEGS/ [1/7]