🚀 Text-to-3D Head Mesh generation in under a minute! 👀 Check out our recent work "CLIP-Head", led by pranav rai , accepted at SIGGRAPH Asia Tech. Comms. - 2023📑 💻 Project Page & Code : raipranav384.github.io/clip_head #ComputerVision #3dmodeling #GenerativeAI

The code and scenes are now available at github.com/ishaanshah/ris….

I will be graduating soon, and am actively looking for research positions. My work is on analytic & neural approaches to physically based rendering, and am also open to working on neural rendering research. Do get in touch if you think I am a good fit: aakashkt.github.io

New meme day

I am looking for PhDs, Postdocs and Interns to explore exciting research in Optics and Generative AI in my new UNC-Chapel Hill lab. Apply now: cs.unc.edu/graduate/gradu… Please share and spread the news :)

MANUS: Markerless Hand-Object Grasp Capture using Articulated 3D Gaussians arxiv.org/pdf/2312.02137…

Thanks for posting our work!

EGSR 2024 will be at Imperial College, London, on July 3rd through 5th. See egsr2024.uk. The Call for Papers is now up, and Ruth Rosenholtz (from MIT and NVIDIA) has accepted our invitation for the first keynote. Hope to see you there!

📢Check out "Relightable Neural Assets"! Our neural representation, combined with explicit geometry, supports full relightability and easy integration into production renderers for assets with highly complex shading. Website: krishnamullia.com/rna

Thanks to last years' real-time glint rendering advances, we can finally render the Penrose Triangle.

I am in Vancouver for the #AAAI2024. What a pleasant suprise to see this slide at inaugural session. One of the 3 Outstanding Papers had 2 authors from IIIT Hyderabad! Both are our BTech-MS Dual-Degree program, essentially undergrad! Congratulations, Nikhil and Shashwat!

Work with Nikhil Chandak, Dominik Peters just won the Outstanding Paper Award🏆at AAAI 2024 (top-3/12000+). We study a framework for making multiple decisions that fairly satisfy diverse preferences. Potential applications range from faculty hiring to how AI combines values🧵👇

Introducing "WordRobe", a method for Text-Guided Generation of Textured 3D Garments. 👕🥼👚👖 Project Page: wordrobe24.github.io/WordRobe_Page arXiv: arxiv.org/abs/2403.17541 (Unroll 👇) #GenerativeAI #3dmodeling #TextToImage

3D Vision Summer School 2024 offers hands-on weeklong deep dive into fundamentals of 3D computer vision and deep learning techniques. Great opportunity to learn from accomplished researchers in the field. Details at 3dvss.github.io #IIITH #IIITB #3d #GenAI

Get ready for the highest quality primer on 3D Computer Vision from some of the greatest minds! 🚀 🚀 🚀 Register Now! ⏰️ P.S. I'll be taking few hands-on sessions. 🙌🏻

Time to share our #SIGGRAPH2024 paper "N-Dimensional Gaussians for Fitting of High Dimensional Functions"! We show that N-Dimensional Gaussian mixtures can be optimized to handle high dimensional inputs like MLPs with a fraction of the training times. sdiolatz.info/ndg-fitting/

Excited to announce that "WordRobe" is accepted ✅ at #ECCV2024 (European Conference on Computer Vision #ECCV2026 ) 🚀🚀🚀🚀🚀

Real-Time Decompression and Rasterization of Massive Point Clouds | Proceedings of the ACM on Computer Graphics and Interactive Techniques dl.acm.org/doi/10.1145/36… This was presented at HPG2024 by Bernhard. Here is the video: youtu.be/DNng_fV0-BY

I made my SSIM implementation public some time back. It is differentiable and 5-8x faster than previous implementations. It was developed as a part of our latest SIGGRAPH Asia '24 paper (humansensinglab.github.io/taming-3dgs/) and has already been integrated into gsplat (nerfstudio).

We are very excited to announce our work "On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images", to be presented at #SIGGRAPH2025! Learn more: repo-sam.inria.fr/nerphys/on-the… 1/3