Pratul Srinivasan @_pratul_
Research Scientist at @GoogleAI. UC Berkeley PhD 2020 + Duke 2014. 3D computer vision + graphics (NeRF!) pratulsrinivasan.github.io San Francisco, CA Joined August 2011-
Tweets74
-
Followers2K
-
Following120
-
Likes481
🎥 What if 3D capture could gracefully handle moving scenes and varying illumination? 🎯Come see how video models generate exactly the data you need at our poster, SimVS! 📍CVPR, June 14th (afternoon), Poster #60.
⚡️ Introducing Bolt3D ⚡️ Bolt3D generates interactive 3D scenes in less than 7 seconds on a single GPU from one or more images. It features a latent diffusion model that *directly* generates 3D Gaussians of seen and unseen regions, without any test time optimization. 🧵👇 (1/9)
🚀 Introducing SimVS: our new method that simplifies 3D capture! 🎯 3D reconstruction assumes consistency—no dynamics or lighting changes—but reality constantly breaks this assumption. ✨ SimVS takes a set of inconsistent images and makes them consistent with a chosen frame.
We’ll be presenting NeRF-Casting at SIGGRAPH Asia next week! NeRF-Casting enables photorealistic rendering of scenes with highly reflective surfaces—something that was previously impossible with models like Zip-NeRF and 3DGS. (1/6)
(1/N) Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering Website: benattal.github.io/flash-cache/ tl;dr our #ECCV2024 (oral ✨) paper presents a new system for inverse rendering that is more physically accurate, and therefore less biased, than existing approaches.
I'm going to present our work at the oral session tomorrow (Wednesday), 9am at #CVPR2024. Come check it out and hang out at the poster session (ours is number 399) immediately after!
I'm going to present our work at the oral session tomorrow (Wednesday), 9am at #CVPR2024. Come check it out and hang out at the poster session (ours is number 399) immediately after!
IllumiNeRF lets you relight objects in 3D. Instead of the classical inverse rendering approach — disentangling the object geometry, materials, and lighting — we use a relighting diffusion model to relight each input image and distill the relit samples into 3D by optimizing a…
IllumiNeRF lets you relight objects in 3D. Instead of the classical inverse rendering approach — disentangling the object geometry, materials, and lighting — we use a relighting diffusion model to relight each input image and distill the relit samples into 3D by optimizing a… https://t.co/kIHuM9hmhT
Wondering how to easily relight an object? Inverse rendering, maybe the first thing that comes to mind, is brittle and expensive due to differentiable Monte Carlo rendering. Check out IllumiNeRF for simple, effective 3D relighting without it! illuminerf.github.io (1/n)
IllumiNeRF enables relighting without expensive inverse rendering. We use a diffusion model trained to relight a single image, and turn its samples into a consistent 3D relit NeRF. With @xmzhao_ (currently on the job market!) @_pratul_ @KeunhongP @rmbrualla @philipphenzler
IllumiNeRF enables relighting without expensive inverse rendering. We use a diffusion model trained to relight a single image, and turn its samples into a consistent 3D relit NeRF. With @xmzhao_ (currently on the job market!) @_pratul_ @KeunhongP @rmbrualla @philipphenzler https://t.co/bSCyZ03FhK
IllumiNeRF 3D Relighting without Inverse Rendering Existing methods for relightable view synthesis -- using a set of images of an object under unknown lighting to recover a 3D representation that can be rendered from novel viewpoints under a target illumination
Check out CAT3D! Image(s)-to-3D in 1 minute! cat3d.github.io Given any number of real or generated images, CAT3D uses a multi-view diffusion prior to create consistent novel views. These views are used to reconstruct a 3D scene using NeRF/3DGS.
Check out CAT3D! Image(s)-to-3D in 1 minute! cat3d.github.io Given any number of real or generated images, CAT3D uses a multi-view diffusion prior to create consistent novel views. These views are used to reconstruct a 3D scene using NeRF/3DGS. https://t.co/PMqBAL1m7s
The cat’s out of the bag! Image(s) to 3D in one minute with a multi-view diffusion model. cat3d.github.io
The cat’s out of the bag! Image(s) to 3D in one minute with a multi-view diffusion model. cat3d.github.io
Videos are cool and all...but everything's more fun when it's interactive. Check out our new project, ✨CAT3D✨, that turns anything (text, image, & more) into interactive 3D scenes! Don't miss the demo!! cat3d.github.io
Videos are cool and all...but everything's more fun when it's interactive. Check out our new project, ✨CAT3D✨, that turns anything (text, image, & more) into interactive 3D scenes! Don't miss the demo!! cat3d.github.io https://t.co/t13Zlc9eSw
🌟 Create anything in 3D! 🌟 Introducing CAT3D: a new method that generates high-fidelity 3D scenes from any number of real or generated images in one minute, powered by multi-view diffusion models. w/ lovely coauthors @holynski_, @poolio and an amazing team!
Scientists, led by a team at Caltech, used AI and telescope data to create the first 3D video of mysterious bright flares around the supermassive black hole at the center of our galaxy. caltech.edu/about/news/ai-…
We just finished a joint code release for CamP (camp-nerf.github.io) and Zip-NeRF (jonbarron.info/zipnerf/). As far as I know, this code is SOTA in terms of image quality (but not speed) among all the radiance field techniques out there. Have fun! github.com/jonbarron/camp…
Introducing Eclipse, a method for recovering lighting and materials even from diffuse objects! The key idea is that standard "NeRF-like" data has all we need: a photographer moving around a scene to capture it causes "accidental" lighting variations. dorverbin.github.io/eclipse/ (1/3)
NeRFs are cool, but they're HARD to edit. Turn 'em into a mesh, and the geometry and UV maps are a dumpster fire -- making simple texture editing mission impossible for your 3D artist. Well, not anymore! Google AI's latest paper Nuvo, employs neural fields for UV mapping,…
🚀 Exciting news from Google Research! Their latest innovation, Nuvo, is changing the game in UV Mapping. Nuvo tackles complex geometries with neural field-based UV mapping, paving the way for more flexible and editable NeRFs and Generative outputs. 🔗neuralradiancefields.io/nuvo-revolutio…
A huge problem with modern radiance field technology (DreamFusion, NeRF, 3DGS, etc) is that the models you recover are damn near impossible for an artist (or an AI) to manually retexture. We fixed this! Excellent new paper from @_pratul_ & co: pratulsrinivasan.github.io/nuvo/

Jon Barron @jon_barron
30K Followers 1K Following AI researcher at Google DeepMind. Synthesized views are my own.
Peyman Milanfar @docmilanfar
94K Followers 501 Following Distinguished Scientist at Google. Computational Imaging, Machine Learning, and Vision. Tweets = personal opinions. May change or disappear over time.
Jia-Bin Huang @jbhuang0604
65K Followers 283 Following
Angjoo Kanazawa @akanazawa
19K Followers 622 Following Assistant Professor at @Berkeley_EECS, @berkeley_ai. KAIR, @nerfstudioteam. Previously advised @WonderDynamics and @LumaLabsAI. she/her.
Frank Dellaert @fdellaert
14K Followers 1K Following Robotics & Computer Vision Professor at Georgia Tech, and part-time CAIO at Verdant Robotics. Before: stints at KUL, Skydio, Facebook B*8, Google AI.
Towaki Takikawa / 瀧... @yongyuanxi
9K Followers 3K Following ceo @outerport (yc s24), former research scientist @nvidia, cs @uwaterloo, phdish @uoft, making technical documents and cad AI-readable
AI葵(Aoi) 🇹🇼Ne... @kwea123
3K Followers 843 Following 我是專門介紹深度學習論文與程式的Vtuber。歡迎合作的邀約(不限V)!Working @LumaLabsAI on NeRF, also doing Vtuber sharing research ideas. Lang: 🇹🇼🇯🇵🇬🇧🇫🇷
Elliott / Shangzhe Wu @elliottszwu
8K Followers 880 Following Assistant Professor @Cambridge_Eng, working on 3D computer vision and inverse graphics, previously postdoc @StanfordSVL, PhD @Oxford_VGG
amit @gravicle
11K Followers 4K Following ceo @LumaLabsAI working on multimodal AGI | prev: built Vision Pro at | everything is figureoutable
Tom Goldstein @tomgoldsteincs
27K Followers 2K Following Professor at UMD. AI security & privacy, algorithmic bias, foundations of ML. Follow me for commentary on state-of-the-art AI.
Bilawal Sidhu @bilawalsidhu
71K Followers 6K Following Merging realities / Mapping the frontier of creation & computing / TED curator / a16z scout / Ex-Google PM (XR, Maps) / 1.6M subs https://t.co/DL3GOP5ZQA
Vincent Sitzmann @vincesitzmann
16K Followers 307 Following Teaching AI to see, model, and interact with our 3D world. Assistant Professor @ MIT, leading the Scene Representation Group (https://t.co/h5gvhLYrtw).
Yuliang Xiu @yuliangxiu
7K Followers 5K Following Assistant Professor @Westlake_Uni, Ph.D. @MPI_IS, previously @USC_ICT. Focusing on democratizing human digitization. Intern @RealityLabs @Ubisoft
𝖒𝖒𝖆𝖑𝖊�... @mmalex
14K Followers 4K Following synth tinkerer (plinky); runway; midjourney; NVResearch (InstantNGP/NeRF); cofounder MediaMolecule (Dreams, LittleBigPlanet); demoscene/vj (statix/bluespoon)
Jonathan Stephens @jonstephens85
11K Followers 1K Following Radiance Fields | Computer Vision | GenAI | Chief Evangelist at @EveryPointIO | Host of the Computer Vision Decoded Podcast
Songyou Peng @songyoupeng
6K Followers 742 Following Spatial intelligence for Gemini and more @GoogleDeepMind. PhD from @ETH and @MPI_IS.
Andrew Davison @AjdDavison
19K Followers 3K Following From SLAM to Spatial AI; Professor of Robot Vision, Imperial College London; Director of the Dyson Robotics Lab; Co-Founder of Slamcore. FREng, FRS.
Mark Boss @markb_boss
1K Followers 223 Following I’m a researcher at Stability AI with research interests in the intersection of machine learning and computer graphics
Simon Green @simesgreen
4K Followers 947 Following Research Engineer @ Meta / Oculus. Computer vision, graphics, NeRFs. Ex-NVIDIA.
Rose @rose_hughes_
319 Followers 3K Following
Sirui Tao @SiruiTao
145 Followers 1K Following CogSci PhD @UCSanDiego Research Design & HCAI in Steven Dow's Protolab Alum in Tzu-mao Li’s Group & Judith Fan's CogTools Lab
Zilu Li @zluleee
238 Followers 314 Following PhD student @UCSD | Prev @Cornell 2024 Computer Graphics & Vision
Riccardo de Lutio @RdeLutio
254 Followers 449 Following Research scientist @NVIDIAAI, outdoors and mountain enthusiast.
NEC Labs America @NECLabsAmerica
921 Followers 4K Following @NEC Labs America delivers high-impact #technology #research. Located in Princeton, NJ & San Jose, CA. #AI #MachineLearning #DataScience #OpticalNetworking
xmeton @xmeton53977
2 Followers 122 Following
Feng @Feng18773980
0 Followers 349 Following
onlyfanssmm @onlyfanssm9404
78 Followers 3K Following Why look anywhere else when you can get top-quality services and products directly from me? Whether it's for personal use or business, I’ve got everything cover
James Maria @jamesmaria01
521 Followers 7K Following Trader trainers and mentors. singel-avid outdoorsman design your off-grid, self reliance 🛰 Enthusiast Co-founder and board member at CoinBase.
New Scientists @awards67811
143 Followers 7K Following Research work, Innovation, exemplifying creativity, impact, and a vision for a better future. #nscawards #phd #researcher website: https://t.co/LlgGrYt7X8
zijz @ItsZijZ
3K Followers 3K Following https://t.co/5fggOEhBEU prodigy and professional at everything
Kevin Kwok @kevinakwok
32K Followers 4K Following
SABEEH @MElkton54569
205 Followers 8K Following Passionate about AI 🤖, ML 🧠, AGI 🌐, ASI 🚀, and robotics 🤖. Never lose hope in God's mercy 💫. AI Engineer Microsoft He studies at MIT. Free Palestine 🇵🇸
Ferdinand Ytteborg @Haiho2Haiho
7 Followers 599 Following
Baibhaw! @daystardreamer
448 Followers 351 Following
Yeasin Arafat @YeasinAraf65121
0 Followers 43 Following
Tagon Sompong @SompongTagon
2 Followers 317 Following
The 69 Controversies ... @69AIControversy
230 Followers 7K Following The 69 Controversies of AI Adoption | Spreading the Word on AI Adoption | From the author of The Last AI @The_Last_AI @s_m_sohn |5/25/25| https://t.co/eMyARc66RG
Yoram Bachrach @yorambac
3K Followers 7K Following Research Scientist at Meta (prev Google DeepMind and Microsoft Research). Working on LLM Agents and Multi-Agent Systems.
Daniel @rn_xiv01
158 Followers 3K Following
Pachito Mani @PacitoMani
356 Followers 4K Following I Have A Dream. - Martin Luther King Jr California 🇺🇸👍🏼
中尾武 Takeru Naka... @takerunakao
2K Followers 6K Following Scientist | MSc(Phys) | Topology Optimization | Generative Design | Metamaterials & XR Devices
Manoj Acharya @manoja328
629 Followers 7K Following Mostly Interested in safe and aligned (neural inspired) Machine Intelligence ; PhD from Rochester Institute of Technology
slashd @slashd
0 Followers 6K Following
Jin Xie @jin_xie52910
3 Followers 467 Following
Abubakar Musa @Abubakarmusamgc
86 Followers 1K Following
HahaHoho @hoh00673007
121 Followers 3K Following
Ywuldom @Ywuldom116
53 Followers 1K Following
Dig Vijay Kumar Yarla... @digvijayky
0 Followers 53 Following AI researcher. PhD student, computer vision & cancer metastasis @Cornell @MSKCancerCenter
jordan @jontonp
16 Followers 972 Following
Basit Mustafa @moltar81435
400 Followers 8K Following introverted but willing to discuss sanctuary moon innovation/ai + dsop/ai delivery @ https://t.co/nQ5pf3TzTZ
× S A K S H I × P A... @Thesakshipandey
20 Followers 180 Following MS by Research Student @iitbombay
Rahel Jhirad @RahelJhirad
2K Followers 8K Following Founder, Imaginator ai knowledge discovery 2D navigation TS ML DL recsys econ math incentives mech design finance networks bridges boundaries, Time, 3d type
Pengboy555 @PengBoy555
2K Followers 8K Following Inexperienced in all subjects so I subject myself to more experience.
ak @unlooted
45 Followers 1K Following
Audrey @audreyctjokro
60 Followers 608 Following thinking of the climate, nutrition, visual arts, computer vision, anthropology, or history 🪷 ml/cv @cornell_tech
Jon Barron @jon_barron
30K Followers 1K Following AI researcher at Google DeepMind. Synthesized views are my own.
Andrej Karpathy @karpathy
1.4M Followers 1K Following Building @EurekaLabsAI. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets.
Peyman Milanfar @docmilanfar
94K Followers 501 Following Distinguished Scientist at Google. Computational Imaging, Machine Learning, and Vision. Tweets = personal opinions. May change or disappear over time.
Angjoo Kanazawa @akanazawa
19K Followers 622 Following Assistant Professor at @Berkeley_EECS, @berkeley_ai. KAIR, @nerfstudioteam. Previously advised @WonderDynamics and @LumaLabsAI. she/her.
Keenan Crane @keenanisalive
38K Followers 485 Following Digital Geometer, Assoc. Prof. of Computer Science & Robotics @CarnegieMellon @SCSatCMU and member of the @GeomCollective. There are four lights.
Frank Dellaert @fdellaert
14K Followers 1K Following Robotics & Computer Vision Professor at Georgia Tech, and part-time CAIO at Verdant Robotics. Before: stints at KUL, Skydio, Facebook B*8, Google AI.
Towaki Takikawa / 瀧... @yongyuanxi
9K Followers 3K Following ceo @outerport (yc s24), former research scientist @nvidia, cs @uwaterloo, phdish @uoft, making technical documents and cad AI-readable
nerfstudio @nerfstudioteam
11K Followers 87 Following A collaboration friendly repo for NeRFs! Discord @ https://t.co/dlC02isi4e | Docs @ https://t.co/DVv9qOgrXL | Github @ https://t.co/MZBSC3KP74
Wenzel Jakob {depreca... @wenzeljakob
8K Followers 283 Following Associate professor leading EPFL's Realistic Graphics Lab. My research involves inverse graphics, material appearance modeling and physically based rendering
Vincent Sitzmann @vincesitzmann
16K Followers 307 Following Teaching AI to see, model, and interact with our 3D world. Assistant Professor @ MIT, leading the Scene Representation Group (https://t.co/h5gvhLYrtw).
𝖒𝖒𝖆𝖑𝖊�... @mmalex
14K Followers 4K Following synth tinkerer (plinky); runway; midjourney; NVResearch (InstantNGP/NeRF); cofounder MediaMolecule (Dreams, LittleBigPlanet); demoscene/vj (statix/bluespoon)
Grant Sanderson @3blue1brown
414K Followers 362 Following Pi creature caretaker. Contact/faq: https://t.co/brZwdQfdif
Steven Brunton @eigensteve
54K Followers 977 Following Teaches math to engineers: https://t.co/TJ5i3Pg678 Professor @UW researching #MachineLearning for #Dynamics and #Control, especially for #FluidDynamics.
Sander Dieleman @sedielem
64K Followers 2K Following Research Scientist at Google DeepMind (WaveNet, Imagen, Veo). I tweet about deep learning (research + software), music, generative models (personal account).
Alec Jacobson @_AlecJacobson
6K Followers 51 Following Associate Professor, Computer Science, University of Toronto; Adobe Research Toronto
Bart Wronski 🇺🇦... @BartWronsk
14K Followers 613 Following Research Scientist at NVIDIA. Follow me: https://t.co/lxEsz7RVRb Ex Google Research, Ex games (Sony, Ubisoft, CD Projekt). Politically leftist. He/they.
Tzu-Mao Li @tzumaoli
1K Followers 343 Following https://t.co/Wk0jKh0Bsy computer graphics, programming systems, machine learning, differentiable graphics
Ben Poole @poolio
21K Followers 1K Following research scientist at google brain. phd in neural nonsense from stanford.
Lilian Weng @lilianweng
166K Followers 166 Following Co-founder of Thinking Machines Lab @thinkymachines; Ex-VP, AI Safety & robotics, applied research @OpenAI; Author of Lil'Log
Jiankui He @Jiankui_He
142K Followers 1 Following Affordable gene therapy. China's Frankenstein 3 years in jail
Ming-Yu Liu @liu_mingyu
9K Followers 506 Following VP of Research at NVIDIA, Head of NVIDIA Deep Imagination Research Lab, IEEE Fellow.
Aditya Kusupati @adityakusupati
5K Followers 2K Following Been places..... Done things.... Next-Gen Modelling @GoogleDeepMind
David Duvenaud @DavidDuvenaud
31K Followers 4K Following Machine learning prof @UofT. Former team lead at Anthropic. Working on generative models, inference, & latent structure.
Jeff Clune @jeffclune
29K Followers 431 Following Professor, CS, U. British Columbia. CIFAR AI Chair, Vector Institute. Sr. Advisor, DeepMind | ML, AI, deep RL, deep learning, AI-Generating Algorithms (AI-GAs)
Stefano Ermon @StefanoErmon
20K Followers 374 Following AI Prof @Stanford | CEO & Cofounder @InceptionAILabs | Co-inventor of DDIM, FlashAttention, DPO, GAIL, and score-based/diffusion models
Masterpieces of Japan @JapanTraCul
127K Followers 101 Following Tap on the images to see in whole or detail. Please bookmark the posts so you can see the favorite works anytime. Subscription gives you info of ukiyoe works.
Floor Eijkelboom @FEijkelboom
1K Followers 235 Following Thinking about Generative Models | PhD candidate at @AmlabUva with @jwvdm and @wellingmax
The Thanatos Archive ... @ThanatosArchive
71K Followers 6K Following Victorian post mortem & mourning photography & objects: https://t.co/Rb5XH6BL1H
でんか@いきも�... @K_theHermit
70K Followers 495 Following ■海洋生物観測所:海のちいさな生物を投稿しています ■東京海洋大学卒:素潜り採集 / 繁殖の記録 /グッズ制作 ■『ヤドカリ探索図鑑』『海のあかちゃん』『海洋生物観測所』『ヤドカリのグラビア』著. marine creatures in Japan.
Lucky Iyinbor @Luckyballa
4K Followers 929 Following Physics Simulation | Geometry Processing | Computer Graphics | AR/VR
Ajay Jain @ajayj_
7K Followers 4K Following Co-founder @genmoai. Co-created denoising diffusion (DDPM), DreamFusion, Dream Fields. Ex Ph.D. @berkeley_ai, @googleai, @facebookai, @nvidiaai, @mit
Ricardo Martin-Bruall... @rmbrualla
3K Followers 704 Following GenAI + 3D || Ex-Google Labs + Project Starline || PhD University of Washington || https://t.co/qYvYBvYxAG
Keunhong Park @KeunhongP
2K Followers 521 Following Building stuff at World Labs. (https://t.co/a81eDVLTNd). @keunhong.bsky.social
Chris Olah @ch402
123K Followers 182 Following Reverse engineering neural networks at @AnthropicAI. Previously @distillpub, OpenAI Clarity Team, Google Brain. Personal account.
Alex Trevithick @alextrevith
553 Followers 300 Following Research Scientist @NVIDIAAI. PhD @UCSanDiego. 4D Vision, Machine Learning, Generative Models.
MathMatize Memes @MathMatize
44K Followers 279 Following Started from the axioms now we’re here. Original memes.
alexandra @brian_eno_69
18K Followers 586 Following
Sanjana Modha @sanjanafeasts
9K Followers 994 Following 🎥Your resident Indian cooking mama 🌟Learn with me on TikTok & IG: Sanjana.Feasts 📚 My cookbook, Sanjana Feasts is out now! ⬇️
Kyle Beaudette @KyleBeautweet
15K Followers 682 Following Author/Illustrator of The Garden Witch https://t.co/W0ty9QMtXv
George Kopanas @gkopanas
3K Followers 424 Following @runwayml fiddling with video models and 3d -- inventor of Gaussian Splatting -- a climbing gym owner back at home -- previously @Google @Adobe @Inria @Arm
Janne Kontkanen @jannekontkanen
182 Followers 109 Following AI & Graphics & Vision at Google DeepMind
Christian Reiser @ChrisJReiser
1K Followers 1K Following KiloNeRF, MERF, Binary Opacity Grids. PhD Student @ Uni Tübingen / MPI-IS. Supervised by Andreas Geiger @AutoVisionGroup. Student researcher at Google DeepMind.
Benjamin Attal @imarhombus
225 Followers 68 Following PhD student @CMU_Robotics, doing research in computer vision, computational imaging. imasquare was taken.
Mac Baconai @Macbaconai
227K Followers 505 Following New Era Aesthetic | Creative Ambassador @perplexity_ai & @LeonardoAi_ | Status: Puilding...
No Context Frogs @nocontextfrogs
171K Followers 143 Following frog guys | rt frog art and frog vids sometimes | I just love cute stuff | dm for credit or delete
Jonathan Gorard @getjonwithit
40K Followers 17 Following Applied mathematician, computational physicist @Princeton Previously @Cambridge_Uni Making the universe computable.
Radiance Fields @RadianceFields
5K Followers 1K Following Documenting the exciting progression of radiance field based technologies, including but not limited to Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting
NTFLX & Drill @NTFLX_and_Drill
2K Followers 2 Following Creating original beats, bars and music videos based on Film and TV characters The only AI is the voice change! Beats in Ableton and animated in blender 😎
Siqi Chen @blader
135K Followers 4K Following 🏗️ Love to build stuff (@runwayco, @sandboxvr, @postmates, @zynga) people love. 💸 Investor @amplitude_hq, @mercury, @owner, @elevenlabsio, @meetgamma ++
Vaughn Tan @vaughn_tan
3K Followers 1K Following uncertainty, not-knowing, open-ended goals, open-ended roles Now: https://t.co/HjUmGnoemk Farcaster: https://t.co/wY16njCHe3
Philipp Henzler @philipphenzler
1K Followers 713 Following Research Scientist @ Google | Generative video models (Veo) / 3D. PhD from UCL