Peter Kocsis @Peter4AI
PhD student at TUM, Visual Computing & Artificial Intelligence Group Munich Joined November 2021-
Tweets256
-
Followers631
-
Following136
-
Likes257
Fantastic retreat this weekend by our research groups! Internal reviews, ideas brainstorming, paper reading, and much more! Of course also many social activities -- the highlight being our kayaking trip - lots of fun :)
So You Want to Be an Academic? A couple of years into your PhD, but wondering: "Am I doing this right?" Most of the advice is aimed at graduating students. But there's far less for junior folks who are still finding their academic path. My candid takes: anandbhattad.github.io/blogs/jr_grads…
🎉Our paper, 𝗜𝗻𝘁𝗿𝗶𝗻𝘀𝗶𝗫, just got accepted to #NeurIPS2025! 🎉 Our model generates renderable PBR maps directly from text and can also be used for rooms-scale scene texturing using SDS. peter-kocsis.github.io/IntrinsiX/ Let's meet in San Diego!
🎉Our paper, 𝗜𝗻𝘁𝗿𝗶𝗻𝘀𝗶𝗫, just got accepted to #NeurIPS2025! 🎉 Our model generates renderable PBR maps directly from text and can also be used for rooms-scale scene texturing using SDS. peter-kocsis.github.io/IntrinsiX/ Let's meet in San Diego!
Can we use video diffusion to generate 3D scenes? 𝐖𝐨𝐫𝐥𝐝𝐄𝐱𝐩𝐥𝐨𝐫𝐞𝐫 (#SIGGRAPHAsia25) creates fully-navigable scenes via autoregressive video generation. Text input -> 3DGS scene output & interactive rendering! 🌍mschneider456.github.io/world-explorer/ 📽️youtu.be/N6NJsNyiv6I
HairGS: Hair Strand Reconstruction based on 3D Gaussian Splatting (#BMVC2025) 📢 We reconstruct realistic 3D hair strands from multi-view images in ~1 hour. Results show robustness to a wide range of hair styles such as challenging curly hair. Project: yimin-pan.github.io/hair-gs/
📢Code release for 3DGS-LM (#ICCV2025)📢 Gaussian-Splatting made faster by changing the underlying optimizer. It's compatible with other changes that accelerate the optimization along different axes. lukashoel.github.io/3DGS-LM/
📢Code release for 3DGS-LM (#ICCV2025)📢 Gaussian-Splatting made faster by changing the underlying optimizer. It's compatible with other changes that accelerate the optimization along different axes. lukashoel.github.io/3DGS-LM/
ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions (#SIGGRAPH) We reconstruct ultra-high fidelity photorealistic 3D avatars capable of generating realistic and high-quality animations including freckles and other fine facial details. We operate on patch-based…
📢 LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans🏠✨ -> converts RGB-D scans into compact, realistic, and interactive 3D scenes — featuring high-quality meshes, PBR materials, and articulated objects. 📷youtu.be/ecK9m3LXg2c 🌍litereality.github.io
Check out our #ICCV2025 work on functional 3d scan editing, learning to optimize, multi-level 3d captioning, interactive mesh editing, audio-driven avatars, & shape matching! Congrats @ElBoudjogh24002, @liuyuehcheng, @chandan__yes, @hcxrli, @shivangi2201, Emery for amazing work!
Amazing in-the-wild video relighting results! I like the quality of the cast shadows, showing that current diffusion models have understanding about light propagation.
Amazing in-the-wild video relighting results! I like the quality of the cast shadows, showing that current diffusion models have understanding about light propagation.
Presenting PrEditor3D at #CVPR2025 📢📢 If you'd like to learn more about our work and discuss 3D generation/editing, come visit our poster on Friday, June 13th, in ExHall D between 10:30-12:30 (Poster #44). Project Page: ziyaerkoc.com/preditor3d
Check out the EnvGS code. Now open-source! Recently added: high-quality real-time GUI rendering to view base color, reflection color, normal map, and depth map. EnvGS performs exceptionally well on highly specular indoor scene reconstruction. Link in the comments! 👇
Check out the EnvGS code. Now open-source! Recently added: high-quality real-time GUI rendering to view base color, reflection color, normal map, and depth map. EnvGS performs exceptionally well on highly specular indoor scene reconstruction. Link in the comments! 👇 https://t.co/rqcXBqXEpQ
📢BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading We propose a hybrid neural shading scheme for creating intrinsically decomposed 3DGS head avatars, that allow real-time relighting and animation. 🌍jonathsch.github.io/becominglit/ 📷youtu.be/xPyeIqKdszA
📢Code Release of Pixel3DMM 📢 Looking for a robust and accurate face tracker? Our state-of-the-art tracker handles challenging in-the-wild settings, such as extreme lighting conditions, fast movements, and occlusions. 👨💻github.com/SimonGiebenhai… 🌍simongiebenhain.github.io/pixel3dmm/
📢PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors📢 We propose a new optimization to up-sample textures of 3D assets (albedo, roughness, metallic, and normal maps) by leveraging 2D super-resolution models. 📝arxiv.org/abs/2506.02846 📽️youtu.be/eaM5S3Mt1RM
Today we're releasing FLUX.1 Kontext - a suite of generative flow matching models that allow you to generate and edit images. Unlike traditional text-to-image models, Kontext understands both text AND images as input, enabling true in-context generation and editing.
📢📢𝐁𝐈𝐆 𝐍𝐄𝐖𝐒: 𝐒𝐮𝐩𝐞𝐫 𝐞𝐱𝐜𝐢𝐭𝐞𝐝 𝐭𝐨 𝐚𝐧𝐧𝐨𝐮𝐧𝐜𝐞 𝐒𝐩𝐀𝐈𝐭𝐢𝐚𝐥 𝐀𝐈 📢📢 We’re building Spatial Foundation Models — a new paradigm of generative AI that reasons about space and time! Really stoked about our world-class team – it’s gonna be mind-boggling!
📢📢𝐁𝐈𝐆 𝐍𝐄𝐖𝐒: 𝐒𝐮𝐩𝐞𝐫 𝐞𝐱𝐜𝐢𝐭𝐞𝐝 𝐭𝐨 𝐚𝐧𝐧𝐨𝐮𝐧𝐜𝐞 𝐒𝐩𝐀𝐈𝐭𝐢𝐚𝐥 𝐀𝐈 📢📢 We’re building Spatial Foundation Models — a new paradigm of generative AI that reasons about space and time! Really stoked about our world-class team – it’s gonna be mind-boggling!
📢 QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization @liuyuehcheng learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction! Project: liu115.github.io/quicksplat
📢GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans📢 We present a novel method to reconstruct hair strands from colorless 3D scans by extracting orientation cues directly from the mesh surface geometry by finding local characteristic lines and from shaded…
📢Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction📢 -> highly accurate face reconstruction by training powerful VITs via surface normals and UV-coordinates estimation. The geometric cues from our 2D foundation model backbone constrain the 3DMM…
Voubies @voubies8083
8 Followers 163 Following
lovelyn @lovelyn242450
55 Followers 487 Following
Roberto Pellerito @RobertoPelleri9
28 Followers 246 Following Robotics and Computer Vision researcher at UZH/ETH Zurich at Robotics and Perception Group, Founder and CTO of @EmemeAI.
Baiba Mennika @BaibaMennika
2K Followers 6K Following Graduated social scientist with knowledge from Scandinavian universities . Hands on experience in journalism. Motto" Brainstorming without brainwashing" MBWB
Andrei Chupakhin @AChupakhin
40 Followers 529 Following PhD Candidate in Computer Science (Lomonosov MSU in Russia). AI Researcher. Runner. Book Lover. I develop my Intellect, Body, and Spirit.
Daniel @rn_xiv01
158 Followers 3K Following
Alexiy Buynitsky @ABuynitsky
89 Followers 1K Following CS @UCSanDiego | ex Persona AI, SpaceX, Armada AI | CS, Math @ Purdue '25
Olaf Dünkel @olaf_duenkel
36 Followers 140 Following ELLIS PhD student with MPI-INF & Uni Oxford https://t.co/sk0jPCW5XP
Anh Nguyen (Aengus) @aengusng8
118 Followers 2K Following Son & brother; AI Research Resident @Qualcomm; Contributor @huggingface🤗; Prev: @VinAI_Research. Update gradients in generative dimensions of computer vision.
Linda Key Carroll @CarrollKey29733
35 Followers 653 Following
Zikrillo Akhror-Murod... @Zikrilloman
571 Followers 6K Following 💼 BDM @ Oddiy Consult & InHunter 🚀 Co-Founder @ LinkPro 🤝🏻 Professional networker 🎓 @UniWestminster 👥 Ex. member @ProductComUz 🪪 citizen @DraperNationHQ
dawut ski @DawutSki36453
10 Followers 380 Following
c @minimal_system
0 Followers 1K Following
Mike Dereviannykh @Mishok2000
677 Followers 1K Following Neural Rendering at Meta, RealityLabs; PhD Student at KIT; ex: Eagle Dynamics, R&D Graphics Engineer.
SAI RAM @rsai31385_ram
25 Followers 2K Following
Odwoluim @Odwoluim329
24 Followers 991 Following
Melanie Coleman @75r38kDyiY7309A
7 Followers 524 Following 30%+ monthly target | 2 high-conviction US stocks. Get instant trade alerts and clear stop/TP. Join now. @Westcsrant
Robert Scoble @Scobleizer
543K Followers 24K Following The best from ML/AI community | Ex-Microsoft, Rackspace, Fast Company | Wrote eight books about the future | Silicon Valley robots, holodecks, BCIs, & startups.
Li Jun @junli66junli66
24 Followers 1K Following
Piotr Ratajski @pratajski
40 Followers 172 Following Welcome to the world of #fintech #insurance,#AI #innovations, where changes bring groundbreaking solutions! 🚀 Innovation #Strategies and Competitive Advantage
云创兽Ai @Blocrui353861
5 Followers 116 Following 🔍 stock investing is my vibe, says this brave girl! eager for trend talks. DM me about swaps trading! ✨ #Finance #Wealth
RockyParadox @RockyParadox44
130 Followers 7K Following
FENG Yang @fy2598099
21 Followers 1K Following
yao lu @yluAIinfra
207 Followers 1K Following Asst Prof. of AI Infrastructure at @NUSingapore | Ex-@MSFTResearch @UW
Katharina Schmid @katha_schmid
14 Followers 28 Following PhD Student @TU_Muenchen Visual Computing & AI Lab
Starc Institute @ARC_Guide
20 Followers 915 Following Starc Institute: A boundaryless academy where talent unites to ignite research and shape the future. https://t.co/mu3ZxzqLnW
SupritamBhattacharya @bhattacharya06
3 Followers 263 Following
John Flynn @johnpeterflynn
19 Followers 117 Following
GPU financing @GPUfinancing
100 Followers 1K Following We help companies scale AI infrastructure through GPU financing, no upfront costs, no delays, just pure compute power.
Vertical Data @Vertical__Data
97 Followers 1K Following Empowering AI innovation with turnkey GPU hardware, colocation, and managed services. Scalable, efficient solutions for your compute needs. 📞+1 (702) 936-3715
YFLiu @Spirit4471
13 Followers 267 Following Rendering algorithm at Xiaohongshu. Master Student from TUDresden, doing research：Computer Graphics and Computer Vision. Opinion are on my own.
Eric Tchirnhausen @tchirnhaus20039
40 Followers 5K Following Like to try new things you never know; trying to prove all software can be automated 😅 😅 😅 | ML/AI, | C++/Java/Go | GitHub : Dyl777
Shareef Khan @Shareef33196383
94 Followers 3K Following
WeiCUI6 @Cui6Wei
37 Followers 767 Following Systems Software Engineer @NVIDIA. Prev @UofT @UCLA @KITE_UHN @Tesla @Samsung @Apple. Working on @NVIDIAGFN
mr_usuff @mr_usuff
56 Followers 1K Following
World Labs @theworldlabs
34K Followers 35 Following World Labs is a spatial intelligence company building Large World Models to perceive, generate, and interact with the 3D world.
M-XR @m_xrstudio
5K Followers 186 Following Capture and measure realistic PBR 3D. Empowering brands, studios, and creators to build virtual worlds. https://t.co/jjaH9J7767 [email protected]
Nataniel Ruiz @natanielruizg
10K Followers 2K Following research @GoogleDeepMind | Veo team | author of DreamBooth | personalization of generative models
Hengshuang Zhao @HengshuangZhao
564 Followers 159 Following Assistant Professor at HKU, previously Postdoc at MIT and Oxford
Moonvalley @moonvalley
3K Followers 13 Following The AI research company advancing visual intelligence through creator partnerships. https://t.co/Xcxrm3gSSQ
Katja Schwarz @K_S_Schwarz
2K Followers 422 Following Generative modeling in 2D and 3D @spAItial_AI. Ex-Meta AI Researcher. Previously PhD at Autonomous Vision Group in Tübingen.
Julius Erbach @JuliusErbach
40 Followers 58 Following Ph.D. candidate at ETH and Max Planck Institute for Informatics
Jonathan Stephens @jonstephens85
11K Followers 1K Following Radiance Fields | Computer Vision | GenAI | Chief Evangelist at @EveryPointIO | Host of the Computer Vision Decoded Podcast
SpAItial AI @SpAItial_AI
2K Followers 5 Following SpAItial is pioneering spatial foundation models (SFMs), a groundbreaking AI paradigm that generates virtual environments that behave like the real world.
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
István Sárándi @Istvan_Sarandi
1K Followers 927 Following Postdoc @ Real Virtual Humans, Uni Tübingen, Germany @uni_tue. PhD from @RWTHVisionLab.
Stan Szymanowicz @StanSzymanowicz
878 Followers 355 Following PhD student @Oxford_VGG | Previously intern @Google @microsoft | @Cambridge_Uni | IYPT 2016 GBR team captain https://t.co/1v3qafo2Sc
Zorah Lähner @ZorahLaehner
594 Followers 290 Following Postdoctoral researcher at the Computer Vision Chair at the University of Siegen
Wojciech Zielonka @w_zielonka
748 Followers 501 Following PhD student @MPI_IS interested in Digital Humans | Previously MSc @TU_Muenchen | https://t.co/e6gpsvKQ0c
Felix Wimbauer @felixwimbauer
721 Followers 302 Following PhD Student @tumcvg, Prev Intern @Meta GenAI, MSc CompSci @UniofOxford, 3D Computer Vision, https://t.co/wh6ywxLvUW
Cheng Lin @_cheng_lin
817 Followers 299 Following Research Scientist | Ph.D. @HKUniversity | Organizer @AnySyn3D 3D Vision, 3D AIGC, Geometric Modeling, Graphics
JennySeidenschwarz @JennySeidensch1
338 Followers 229 Following PhD Student at Dynamic Vision and Learning Group, Technical University of Munich
International Confere... @3DVconf
6K Followers 230 Following Official account for International Conference on 3D Vision (3DV) #3DV2026 🇨🇦 Hosts @hanwenjiang1 @yan_xg @ZhiHaoLin16 @CSProfKGD
Zian Wang @zianwang97
950 Followers 152 Following research scientist @NVIDIA, phd candidate @UofT @VectorInst
Ferenc Huszár @fhuszar
42K Followers 1K Following Secular Bayesian. Professor of Machine Learning @Cambridge_CL. Talent aficionado at https://t.co/RbJkoLguey Alum of @Twitter, Magic Pony and @Balderton
Anand Bhattad @anand_bhattad
3K Followers 438 Following Assistant Professor @JHUCompSci, @HopkinsDSAI Past: RAP @TTIC_Connect | PhD @SiebelSchool Research: Exploring Knowledge in Generative Models
Jan @JDihlmann
346 Followers 425 Following Researching 3D Reconstruction & Generation | PhD Student University of Tübingen @CG_Tuebingen & @MPI_IS | Previously @saysomapp
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
Andreas Engelhardt @AjlEngelhardt
34 Followers 42 Following
Eric Dexheimer @eric_dexheimer
672 Followers 276 Following PhD student at Dyson Robotics Lab, Imperial College London
Sanja Fidler @FidlerSanja
16K Followers 491 Following Associate Professor @UofT, Vice President of AI Research @nvidia, founding member of @VectorInst. Computer vision, deep learning, 3D. Opinions are my own.
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.
Paul Debevec @debfx
8K Followers 484 Following Cheif Research Officer, Eyeline Studios Adjunct Research Professor, USC ICT Visual Effects Branch, Academy of Motion Pictures
Georgia Gkioxari @georgiagkioxari
11K Followers 456 Following Assistant professor in Computing + Mathematical Sciences @Caltech 🏛️ ∙ Computer vision enthusiast 🤖 ∙ Part-time at @metaai 👩🏻💻∙ From 🇬🇷
Balamurugan Thambiraj... @balathambiraja
291 Followers 319 Following Intern at Amazon, Sunnyvale | Ph.D. student part of MPI-IS NCS group working on synthesis of motion for digit humans for AR/VR applications
Gwangbin Bae @BaeGwangbin
782 Followers 203 Following Senior ML Engineer @tesla / former PostDoc at Dyson Robotics Lab @imperialcollege / PhD in Computer Vision @Cambridge_Eng
Arash Vahdat @ArashVahdat
10K Followers 877 Following Research Director, leading fundamental generative AI research (GenAIR) @nvidia research, views are my own.
Kosta Derpanis @CSProfKGD
69K Followers 197 Following #CS Assoc Prof @YorkUniversity, #ComputerVision Scientist Samsung #AI, @VectorInst Faculty Affiliate, TPAMI AE, @ELLISforEurope Member #ICCV2025 Publicity Chair
Desai Xie - on the jo... @desaixie1999
215 Followers 260 Following CS PhD candidate @ SBU. Intern @AdobeResearch, @ ByteDance Seed. Visual generative models (3D, video), large-scale training, RL.
Gordon Wetzstein @GordonWetzstein
4K Followers 41 Following
ACM SIGGRAPH @siggraph
43K Followers 2K Following Official Twitter for @TheOfficialACM's Special Interest Group on Computer Graphics & Interactive Techniques + its conferences. #SIGGRAPH2025 #SIGGRAPHAsia2025
SIGGRAPH Asia ➡️ ... @SIGGRAPHAsia
5K Followers 3K Following The official Twitter account for ACM #SIGGRAPHAsia2025 ➤ 15 – 18 Dec 2025 at HKCEC, Hong Kong.
Marc Benedí @marcbenedi
299 Followers 345 Following PhD Candidate @ TU Munich Visual Computing & Artificial Intelligence Group w/ Matthias Niessner. Previously CS @ UPC - FIB
Investing.com @Investingcom
1.3M Followers 311 Following 📍TAP HERE FOR INVESTING PRO PLANS :https://t.co/WvAMcbOXmF
Jim Fan @DrJimFan
327K Followers 3K Following NVIDIA Director of Robotics & Distinguished Scientist. Co-Lead of GEAR lab. Solving Physical AGI, one motor at a time. Stanford Ph.D. OpenAI's 1st intern.
#ICCV2025 @ICCVConference
11K Followers 63 Following Official account for the IEEE/CVF International Conference on Computer Vision. #ICCV2025 Honolulu 🇺🇸 Hosted by @natanielruizg @anfurnari @YVinker @CSProfKGD
Chandan Yeshwanth @chandan__yes
335 Followers 178 Following PhD Candidate at 3D Understanding Lab, TUM. Building models for indoor scene understanding through multimodal data and natural language
Tobias Kirschstein @TobiasKirschst1
622 Followers 92 Following PhD Student at the Visual Computing & Artificial Intelligence Lab @ TUMTrends for United States
You might like
