📢 Happy to share that our work, 𝗘𝗔𝗦𝗜-𝗧𝗲𝘅, on single image guided 3D mesh texturing, has been accepted as a Journal (ACM TOG) paper at #SIGGRAPH2024. 🥳 🌎 Project Page: sairajk.github.io/easi-tex/ A collaboration with Yizhi Wang, @mahdavi_amiri, and Hao (Richard) Zhang.

We will be presenting BANF during the Friday morning session @CVPR24. Don’t miss out! Poster #99

Excited to share our new work 😊 VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control My main research interest is 4D generation, and a promising way towards realistic 4D scenes is through 3D extended video models! snap-research.github.io/vd3d Thanks AK!

I’d love to humbly introduce you to something we believe is going to be a game changer for both VR and VFX. When I first tried it I couldn’t take a headset off for like 10 mins. The hair, the dress, the movements — your brain just can’t stop being mesmerized. Tech thread 🔽

📢📢📢 𝐋𝐚𝐠𝐫𝐚𝐧𝐠𝐢𝐚𝐧 𝐇𝐚𝐬𝐡𝐢𝐧𝐠 𝐟𝐨𝐫 𝐂𝐨𝐦𝐩𝐫𝐞𝐬𝐬𝐞𝐝 𝐍𝐞𝐮𝐫𝐚𝐥 𝐅𝐢𝐞𝐥𝐝 𝐑𝐞𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧𝐬 at #ECCV2024 Project led by: Shrisudhan Govindarajan (Shrisudhan Govindarajan) and Zeno Sambugaro (Zeno Sambugaro) theialab.github.io/laghashes arxiv.org/abs/2409.05334

1/6 Introducing SDI or Score Distillation via Reparametrized DDIM, a new approach for 3D generation using diffusion models that brings 3D generation quality closer to that of 2D! Joint with Haitz Sáez de Ocáriz Borde Kristjan Greenewald Vitor Guizilini Timur Bagautdinov Vincent Sitzmann Justin Solomon

Blendify 2.0 is out!🎉 This major release of our Python framework for creating and rendering scenes in Blender introduces several new features. More details below 🧵 (1/3). GitHub: github.com/ptrvilya/blend… Developed together with Vladimir Guzov.

📢 Excited to share our new work: AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers snap-research.github.io/ac3d We analyze what pre-trained video diffusion transformers understand about 3D and demonstrate dynamic scene generation with 3D control.

📢📢📢 RoMo: Robust Motion Segmentation Improves Structure from Motion romosfm.github.io arxiv.org/pdf/2411.18650 TL;DR: boost your SfM pipeline on dynamic scenes. We use epipolar cues + SAMv2 features to find robust masks for moving objects in a zero-shot manner. 🧵👇

Here's one to read on your flight to #NeurIPS2024! A flow-matching transformer model in function space! This model has all the advantages of neural fields: resolution-free generation and domain-agnostic architecture, while obtaining strong results on ImageNet-256 and Objaverse!

📢📢📢 "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing", a mesh-based 3D represention. radfoam.github.io arxiv.org/abs/2502.01157 Co-lead by my PhD students Shrisudhan Govindarajan and Daniel Rebain, and w/ Kwang Moo Yi

Thanks for sharing MrNeRF ! TL;DR - Sparse Views to Dynamic 3D generation. Key Insight - Slowing a video (magnifying temporally) improves 3D generation quality.

Check out my first PhD paper!

While we are going back to the era of research… Introducing 𝗗𝗲𝗲𝗽 𝗜𝗺𝗽𝗿𝗼𝘃𝗲𝗺𝗲𝗻𝘁 𝗦𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗶𝗼𝗻 (𝗗𝗜𝗦) – a new learning method for recursive reasoning. DIS builds on the elegant Tiny Recursive Model (TRM)(Alexia Jolicoeur-Martineau) but makes recursion radically simpler:

🚀 I’m excited to share my final work as a PhD student: 𝙈𝙚𝙨𝙝𝙎𝙥𝙡𝙖𝙩𝙩𝙞𝙣𝙜: 𝘿𝙞𝙛𝙛𝙚𝙧𝙚𝙣𝙩𝙞𝙖𝙗𝙡𝙚 𝙍𝙚𝙣𝙙𝙚𝙧𝙞𝙣𝙜 𝙬𝙞𝙩𝙝 𝙊𝙥𝙖𝙦𝙪𝙚 𝙈𝙚𝙨𝙝𝙚𝙨 - Arxiv: arxiv.org/abs/2512.06818 - Code: github.com/meshsplatting/… - Project page: meshsplatting.github.io