#CVPR2023 paper by R. A. Rosu and S. Behnke: "PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices" radualexandru.github.io/permuto_sdf

We have an interesting work at Eurographics Symposium on Rendering: Efficiently rendering human hair, with controlled use of MLPs. Smartly embedding NNs in rendering is a recent trend, and works pretty well. Work done as part of my internship with Meta Reality Labs. aakashkt.github.io/hair_high_orde…

⚠ The most important NeRF project I've seen since Zip-NeRF! ⚠ This team solved a plaguing problem that I run into: NeRFing long, linear, forward-facing image sets! Now I can NeRF alleyways and streets! The trick here is 2-fold 1️⃣ Creating multiple-local radiance fields along

Excited to share our work “NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation” at #CVPR2023 ziyanw1.github.io/neuwigs/ W/ my brilliant collaborators Giljoo Nam Tuur Stuyck Stephen Lombardi, Chen Cao, Jason Saragih, Michael Zollhoefer Jessica Hodgins Christoph Lassner

🤲Interested in real-time relighting, 3D hands, and digital humans? Come to see our #CVPR2023 poster (#18) of RelightableHands this morning!

The code for our project is up! We have released implementations of path tracing (of course) and an implementation of Neural Radiance Caching (NRC), along with our method. Do check out if any of these are useful for you! github.com/facebookresear…

🎉Excitied to share our #SIGGRAPH2023 work "CT2Hair: High-Fidelity 3D Hair Modeling using Computed Tomography". Project page: jhonve.github.io/CTHair Code: github.com/facebookresear…

🎉 We just released code, data and model for our #SIGGRAPH2023 work "CT2Hair"!! CT2Hair achieves fully automatic reconstruction of production-ready hair strands from computed tomography (CT) scans!! Code&Data: github.com/facebookresear… Project: yuefanshen.net/CTHair

Here's my conversation with Mark Zuckerberg, his 3rd time on the podcast, but this time we talked in the Metaverse as photorealistic avatars. This was one of the most incredible experiences of my life. It really felt like we were talking in-person, but we were miles apart 🤯 It's

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

Introducing VR-NeRF (SIGGRAPH Asia ➡️ Hong Kong 2023): 🤩 multi-camera rig for multi-view HDR capture 🤓 perceptual HDR optimization + level of detail 😎 real-time multi-GPU VR rendering Project: vr-nerf.github.io Paper: arxiv.org/abs/2311.02542 Dataset: github.com/facebookresear…

📢 Check out 𝗥𝗲𝗹𝗶𝗴𝗵𝘁𝗮𝗯𝗹𝗲 𝗚𝗮𝘂𝘀𝘀𝗶𝗮𝗻 𝗖𝗼𝗱𝗲𝗰 𝗔𝘃𝗮𝘁𝗮𝗿𝘀! Our latest codec avatars using 3D Gaussians generalize to novel lighting (OLAT, envmap) with *all-frequency* reflection (see video for hair and eye reflection) in real-time! shunsukesaito.github.io/rgca/

🚨 InterHandGen (#CVPR2024) is one of the first works on the generative modeling of 🤲interacting two hands (with or without an additional object). This diffusion-based prior be incorporated into any existing method via SDS-like loss to boost the estimation accuracy! (1/🧵)

Sharing "Perm: A Parametric Representation for Multi-Style 3D Hair Modeling"! Aiming to be the SMPL for 3D hair, it has disentangled parameters to control hair cut types and curl patterns, a generic prior for single-view reconstruction and hair-conditioned image generation. We've

I'm happy to announce Gaussian Haircut✂️, our recent hair reconstruction work that will appear at #ECCV2024! We'll present it in the Thursday afternoon session. Project page: eth-ait.github.io/GaussianHaircut The code is coming soon!