Neural Fields

Flying with Photons: Rendering Novel Views of Propagating Light Authors: Anagh Malik, Noah Juravsky, Ryan Po, Gordon Wetzstein, Kiriakos N. Kutulakos, David B. Lindell anaghmalik.com/FlyingWithPhot…

Happy New Year!✨We have released #colmap poses of 10/75 scenes for our #ICCV2023 paper NEO-360🔥. Check it out to test your own #GaussianSplatting and #NeRF algorithms (a sample #GaussianSplat shown below): github.com/zubair-irshad/… @ToyotaResearch @ICatGT @mlatgt @neural_fields

📢 Excited to share our latest work on computing accurate differential operators for hybrid neural fields (like Instant NGP)! 🔗: justachetan.github.io/hnf-derivative… 🧵👇🏻 (1/n)

📢Our new @NVIDIAAI paper is out! I'm happy to share Compact NGP with Learned Hash Probing, which offers NeRFs that are 3.5x smaller than Instant NGP at a ~1.26x training cost and equivalent (or faster) inference speeds! 🌐: nv-tlabs.github.io/compact-ngp/ 🎥: youtube.com/watch?v=3TEry8…

🌟We have released NeO-360 code -github.com/zubair-irshad/…. NeO-360 achieves generalizable outdoor 360-degree novel view synthesis. We hope the code and NERDS360 dataset advances digital twins of unbounded spaces! @ToyotaResearch @ICatGT @GTrobotics @mlatgt @neural_fields

Have you ever been outside?🏞️I hear it's big🏙️Scaling high detail neural rendering requires efficient parallel optimization of the scene _and_ its cameras📸 #SIGGRAPHAsia2023 - Friday 10:15am in C4.8 in Sydney! xchaowu.github.io/papers/scanerf/ @neural_fields

Our paper has been published in Communications Materials! We have developed a neural field-based crystal structure decoder inspired by recent 3D vision research (3D object recognition and neural fields). Paper: nature.com/articles/s4324… GitHub: github.com/omron-sinicx/n…

Excited to be at @SIGGRAPHAsia! Our work, "DreamEditor: Text-Driven 3D Scene Editing with Neural Fields", led by @JjZhuang26958 @chenwangcw, will be presented at 14-15 today in C4.11. Come chat with us about Neural Representations and 3D Generative Models!

#SIGGRAPHAsia2023 #NeuralPDE Neural Stress Field is a reduced-order modeling framework for solid, fluid, and fracture mechanics. After training, it enables 10X speedup for simulations of tearing and other damage phenomena to everyday materials such as bread! Come to the NEURAL PHYSICS session on Thursday to see Zeshun’s first-ever SIGGRAPH paper 🚀 Great collaboration w/ @xuanli917 @minchen_li_ @kcarlberg @chenfanfujiang and folks at @uclamath @SCSatCMU @UofTCompSci @MIT_CSAIL @Meta @RealityLab zeshunzong.github.io/reduced-order-… asia.siggraph.org/2023/presentat…

Today at #NeurIPS2023 I will be presenting our work on "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields". Join us at poster session 3 on Wednesday morning, poster #619. Paper: arxiv.org/abs/2310.20679 Source code: github.com/mkofinas/aether [1/8] 🧵

Our paper, NSF (neural stress field), will be presented on SIGGRAPH Asia this week by Professor @YinYang24414350 ! Check it out if you are interested!

📢 I will be at NeurIPS 🛫next week! If you are attending and are interested in 3D Vision, Dynamic Scenes, and Neural Fields then please do reach out! Would love to get to know more about your work 😄 Would also love to meet people and chat about PhD life, or just grab good ☕️!

Neural Field Convolutions by Repeated Differentiation Authors: Ntumba Elie Nsampi, Adarsh Djeacoumar, Hans-Peter Seidel, Tobias Ritschel, Thomas Leimkühler dl.acm.org/doi/abs/10.114…

【#CGWCC2023】 OnePlanetによる「XRコンテンツにおけるNeRFの活用方法」配信中！ ▼視聴はこちら cgworld.jp/special/cgwcc2… XRコンテンツにおけるNeRF（Neural Radiance Fields）の活用事例を解説いただいてます！

RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency Zhuoman Liu, Bo Yang tl;dr: ray-surface distance field->3D shape; dual-ray visibility classifier->spatial relationships of any pair of rays->multi-view geometry consistent arxiv.org/pdf/2310.19629…

Our #RayDF at #NeurIPS2023, a simple ray-based representation, directly inferring surface points, 1000x faster than OF/SDF/UDF/NeRF in rendering. Project: vlar-group.github.io/RayDF.html Thx to @zhenjun_zhao Grateful if awesome guys @_akhaliq @ducha_aiki @neural_fields could retweet😅