Edgar Sucar @SucarEdgar
Postdoc @Oxford_VGG PhD Dyson Robotics Lab at Imperial College edgarsucar.github.io Oxford, UK Joined April 2017-
Tweets105
-
Followers699
-
Following1K
-
Likes4K
Delighted to share the first project of my PhD, "Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction". We show unprecedented capabilities of synthesizing novel lidar scans from as few as 2 input views! 🖥️anaghmalik.com/TransientNeRF
Congratulations to Edgar who passed his PhD viva today, and thanks to examiners @tolga_birdal and José María Montiel! A reminder of Edgar's iMAP, a landmark as the first real-time neural field SLAM system from #ICCV2021.
Congratulations to Edgar who passed his PhD viva today, and thanks to examiners @tolga_birdal and José María Montiel! A reminder of Edgar's iMAP, a landmark as the first real-time neural field SLAM system from #ICCV2021.
vMAP: Vectorised Object Mapping for Neural Field SLAM, new at #CVPR2023! Each object is represented by a separate MLP, optimised in parallel via vectorised training. Full info: kxhit.github.io/vMAP Dyson Robotics Lab, Imperial College, @liu_shikun, Marwan Taher, @AjdDavison.
Excited to announce "Learning a Depth Covariance Function" with @AjdDavison. A flexible framework for a variety of geometric vision tasks, such as dense monocular visual odometry shown below. Dyson Robotics Lab, Imperial College Project page: edexheim.github.io/depth_cov/ #CVPR2023
What is ChatGPT doing ... and why does it work? From the lore of neural nets to what Aristotle didn't get to ... here's my version of the story: writings.stephenwolfram.com/2023/02/what-i…
Our work on leveraging general pre-trained feature extractors for open-set real-time scene understanding has been accepted for #ICRA2023! Joint work with @SucarEdgar @AjdDavison Check out project page: makezur.github.io/FeatureRealist…
Our work on leveraging general pre-trained feature extractors for open-set real-time scene understanding has been accepted for #ICRA2023! Joint work with @SucarEdgar @AjdDavison Check out project page: makezur.github.io/FeatureRealist…
If you're at CORL this week in NZ come and meet @iainhaughton and @Ed__Johns and see Iain's presentation in the oral session on Saturday. Dense, fully automatic segmentation of scene properties like softness via real-time neural field training; no priors! It's iLabel for robots.
If you're at CORL this week in NZ come and meet @iainhaughton and @Ed__Johns and see Iain's presentation in the oral session on Saturday. Dense, fully automatic segmentation of scene properties like softness via real-time neural field training; no priors! It's iLabel for robots. https://t.co/aJ7EzqyZ0b
#CORL2022 oral: mapping non-visual properties (material, softness, force) from very few point sensor tests. iLabel-like neural field produces dense maps + guides actions. Live, autonomous, no priors! @iainhaughton et al, @Dyson @ICComputing. Paper/video: ihaughton.github.io/RobE/
New: Feature-realistic neural fusion for real-time, open set scene understanding. Our neural field renders to feature space, enabling real-time grouping and segmentation of similar objects or parts from ultra-sparse, online interaction. Dyson Robotics Lab. makezur.github.io/FeatureRealist…
"A Year" AI animation artwork made in colab using my custom stable 3D animation algorithm on top of #stablediffusion model. In the thread I share some details about the algo and when i plan to release it, and talk about the joy and future of AI filmmaking 🎶 DakhaBrakha - Vesna
cool work by Dominic Maggio and collaborators on real-time robot localization using Neural Radiance Fields (NeRF) with Monte Carlo Localization: youtu.be/yIgl3kbpbXY (link to full paper in the video description) #mitSparkLab #NeRF #neuralFields #robotics #localization
Glad to see @SucarEdgar, @AjdDavison "Implicit Mapping and Positioning in Real-time" highlighted in the Neural Fields in Robotics tutorial at #cvpr2022 Take a look at the project here edgarsucar.github.io/iMAP/
NICE-SLAM: a hybrid representation of feature voxels plus MLP allows neural mapping to scale to larger scenes. Similar representation to Instant-NGP, minus hashing and with a pretrained decoder. Wondering what is the advantage of pretraining the MLP decoder?
NICE-SLAM: a hybrid representation of feature voxels plus MLP allows neural mapping to scale to larger scenes. Similar representation to Instant-NGP, minus hashing and with a pretrained decoder. Wondering what is the advantage of pretraining the MLP decoder?
iSDF shows how to reconstruct a full signed distance function through optimisation of a Neural Field, by bounding SDF predictions with depth surface measurements. This representation is particularly exciting for applications in robot planning.
iSDF shows how to reconstruct a full signed distance function through optimisation of a Neural Field, by bounding SDF predictions with depth surface measurements. This representation is particularly exciting for applications in robot planning.
Andrew Davison @AjdDavison
16K Followers 2K 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.Frank Dellaert @fdellaert
11K Followers 1K Following CTO at Verdant Robotics, Robotics & Computer Vision Professor at Georgia Tech (on leave). Before: sabbatical at KUL, stints at Skydio, Facebook B*8, Google AI.Jim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Luca Carlone @lucacarlone1
8K Followers 508 Following Associate Professor at MIT, SPARK Lab Director, Roboticist, interested in how machines see and understand the world (he/his/him)Soumith Chintala @soumithchintala
186K Followers 877 Following Cofounded and lead @PyTorch at Meta. Also dabble in robotics at NYU. AI is delicious when it is accessible and open-source.Antoni Rosinol @RosinolToni
2K Followers 730 Following Co-Founder @StackAI_HQ (YC W23) | PhD @MIT | LLMs & Computer Vision | https://t.co/5irrHUYiJmYuliang Xiu @yuliangxiu
5K Followers 4K Following Ph.D. in Vision & Graphics @MPI_IS, previously @USC_ICT. Focusing on democratizing human-centric digitization. Intern at @RealityLabs @UbisoftYizhak Ben-Shabat (It.. @sitzikbs
1K Followers 812 Following 🇮🇱 Researcher / Educator / Father / Podcaster. Creator of 3D computer vision algorithms. Follow the podcast feed at @talking_papers.Evelynn Trillana @evelynn8589
83 Followers 5K FollowingJung Yejin @jjjjjjahah
0 Followers 2 FollowingDenisse Erkkila @DErkkila27999
109 Followers 5K FollowingEmmy Mcglothlen @McglothleEm
43 Followers 5K FollowingRoslyn Dorough @RoslyDorou
35 Followers 5K FollowingSummer Torralba @SummerTorr47739
71 Followers 5K FollowingSumayyah Jurisch @s_sumayy
70 Followers 5K FollowingSia Weyler @weyle_sia
16 Followers 3K FollowingGaynor Peleg @GaynorPele51459
71 Followers 5K FollowingLore Mauss @LoreMauss66252
38 Followers 5K FollowingNoura Vandermoon @NVandermoo
53 Followers 5K FollowingAlejandra Esson @AlejandrEsso
36 Followers 5K FollowingEliza Disalvi @el_disal
63 Followers 5K FollowingEfa Fregoe @EfaFregoe21264
92 Followers 5K Followingms. emma summer @summerbrennnan
556 Followers 3K Following C-19 Pndmc.Floyd. Starkweather. EvrGvn. Huan-Seaf00d. EvrGrnMrn. March.Breathrs.Junetnth. HtwveWildfire.Vaxx.Vrnts.Ukr-Ru'23-. IS-Nahel? CoroX. 2024Karyl Fregeau @freg_kar
64 Followers 5K FollowingZainab Lizaola @lizao_zai
31 Followers 5K FollowingPOM @pom_I_moq
4K Followers 2K Following Working with a ragtag group of nerds to build a small piece of The 2nd Renaissance @banodoco.Han Xue @HanXue012
119 Followers 487 Following Ph.D. student @sjtu1896 | Interesed in Robotics & 3D VisionEliana Pautler @EPautle
47 Followers 5K FollowingCarlos Pinheiro @Capsbrr
22 Followers 391 FollowingLeota Penunuri @PenunLeo
70 Followers 5K FollowingAman i @Amani870107
21 Followers 1K FollowingBetsey Trickel @bets_trick
62 Followers 5K FollowingJuniper Frondorf @JFrondor
80 Followers 5K FollowingTera Ripperger @ripperg_t
81 Followers 5K FollowingMichelina Caldarera @CaldareMicheli
55 Followers 5K FollowingMarissa Baynham @BaynhMaris
9 Followers 3K FollowingMarva Rubinow @marva36730
76 Followers 5K FollowingStacie Baugus @baug_stac
65 Followers 5K FollowingZina Goulas @goulas92294
86 Followers 5K FollowingCallum Rhodes @DoC_Rhodes_
27 Followers 46 Following Post doc @ Dyson Robotics lab, Imperial College LondonKodi Saturnio @KodiSaturn47133
77 Followers 5K FollowingMia-rose Leaser @LeaserMia26628
84 Followers 5K FollowingJoni Silvestri @JoniS3169
78 Followers 5K FollowingSusanne Connin @ConninSusa11918
85 Followers 5K FollowingJasmin Cronquist @JCronquis
30 Followers 5K FollowingShea Spengler @ShSpengl
29 Followers 5K FollowingIsla-rose Nagode @IslaNagode73404
84 Followers 5K FollowingKatherine Bungo @BunKather
34 Followers 5K FollowingAK @_akhaliq
309K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxDmytro Mishkin 🇺�.. @ducha_aiki
18K Followers 591 Following Marrying classical CV and Deep Learning. I do things, which work, rather than being novel, but not working.Matthias Niessner @MattNiessner
31K Followers 162 Following Professor for Visual Computing & Artificial Intelligence @TU_Muenchen Co-Founder @synthesiaIOAndrew Davison @AjdDavison
16K Followers 2K 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.Andrej Karpathy @karpathy
978K Followers 904 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥Yann LeCun @ylecun
710K Followers 718 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Michael Black @Michael_J_Black
58K Followers 638 Following Director, Max Planck Institute for Intelligent Systems (@MPI_IS). Chief Scientist @meshcapade. Building 3D digital humans using vision, graphics, and learning.Kosta Derpanis @CSProfKGD
48K Followers 198 Following #CS Associate Prof @YorkUniversity, #ComputerVision Scientist Samsung #AI, @VectorInst Faculty Affiliate, TPAMI AE, #CVPR2024/#ECCV2024 Publicity Co-chairFrank Dellaert @fdellaert
11K Followers 1K Following CTO at Verdant Robotics, Robotics & Computer Vision Professor at Georgia Tech (on leave). Before: sabbatical at KUL, stints at Skydio, Facebook B*8, Google AI.Autonomous Vision Gro.. @AutoVisionGroup
12K Followers 371 Following Awesome Vision Group of Andreas Geiger at the University of Tübingen. We are excited about Computer Vision, Machine Learning and Robotics.François Chollet @fchollet
469K Followers 770 Following Deep learning @google. Creator of Keras. Author of 'Deep Learning with Python'. Opinions are my own.Andrea Tagliasacchi �.. @taiyasaki
12K Followers 165 Following Associate Professor @ SFU (Research Chair), Research Scientist @ Google DeepMind, Associate Professor (status only) @ UofT. Opinions are my own.Jim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Luma AI @LumaLabsAI
79K Followers 49 Following Luma's mission is to build multimodal AI to expand human imagination and capabilities. Join us → https://t.co/amvw1U21NcEric Brachmann @eric_brachmann
4K Followers 592 Following Staff Scientist @NianticLabs. Throws #MachineLearning at traditional #ComputerVision pipelines to see what sticks. Differentiates the non-differentiable.Yi Ma @YiMaTweets
71K Followers 123 Following Chair Professor in AI, Director of IDS, Head of CS, HKU; Professor of EECS, Berkeley; Author of Book: High-Dim Data Analysis, https://t.co/gwaqMJp8av.Lucas Beyer (bl16) @giffmana
56K Followers 444 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]Barsee 🐶 @heyBarsee
259K Followers 775 Following Daily tweets on the latest AI and Tech developments to stay ahead of the curve | Founder of https://t.co/bpf7DytcqjAndrew Brown @Andrew__Brown__
1K Followers 440 Following Senior Research Scientist GenAI @AIatMeta working on visual generation | PhD @Oxford_VGG with Andrew Zisserman, Previously @oxengsciPhilipp Schmid @_philschmid
16K Followers 649 Following Tech Lead and LLMs at @huggingface 👨🏻💻 🤗 AWS ML Hero 🦸🏻 | Cloud & ML enthusiast | 📍Nuremberg | 🇩🇪 https://t.co/l1ppq3q3hkInfinite-Realities @8Infinite8
9K Followers 2K Following Building Photometric and Motion Scanning Systems Since 2009. We specialize in digital humans. https://t.co/YUKnRuMZs5 | https://t.co/a5Cod9UHBPAston Zhang @astonzhangAZ
5K Followers 92 Following Research Scientist at the #llama team of Meta Generative AI, designing and training large language models. Opinions are my own.Ishan Misra @imisra_
5K Followers 209 Following GenAI@Meta | MIT TR's 35 under 35 | Emu Video, ImageBind, DINO, BarlowTwinsAna Dodik @ana_dodik
1K Followers 730 Following Geometry Processing PhD student @ MIT CSAIL. Prev. Meta, Disney Research. Mother of a half-dog, half-tornado. 🌈 she/herAhmad Al-Dahle @Ahmad_Al_Dahle
4K Followers 52 Following #Girldad of twins. Leading GenAI @ Meta (llama, imagine, meta ai and more)dwight @dwightchurchill
1K Followers 736 Following cofounder of @getcaptionsapp -- fmr @goldmansachs + alum @recursecenter. from the great state of nh.OATML_Oxford @OATML_Oxford
5K Followers 125 Following Oxford Applied and Theoretical Machine Learning GroupAndres Freund (Tech) @AndresFreundTec
9K Followers 105 Following FWD: @[email protected] Postgres developer, working at Microsoft. For politics: @AndresFreundPolVikash Kumar ✈️IC.. @Vikashplus
4K Followers 406 Following Studying intelligent embodied behaviors. Ad. Prof. @CMU_Robotic | Sr. research scientist at @AIatMeta @GoogleAI @OpenAI | @berkeley_ai @UWcse #MuJoCoBanodoco @banodoco
874 Followers 15 Following A community of artists & engineers working to help the open AI art ecosystem thrive. Art auto-posted from our Discord: https://t.co/Zm17NaE67lPOM @pom_I_moq
4K Followers 2K Following Working with a ragtag group of nerds to build a small piece of The 2nd Renaissance @banodoco.Noam Brown @polynoamial
34K Followers 611 Following Researching reasoning @OpenAI | Co-created Libratus/Pluribus, the first superhuman no-limit poker AIs | Co-created CICERO | PhD from @SCSatCMUJules Urbach @JulesUrbach
30K Followers 11 Following Founder and CEO - @OTOY Inc. | #RENDER | https://t.co/OTL1xZiTD0The Render Network @rendernetwork
184K Followers 271 Following The Render Network connects artists looking to render next-gen 3D media with near unlimited GPUs in a decentralized global network. AI GPU's next #rendernetworkKostas Daniilidis @KostasPenn
4K Followers 1K Following Ruth Yalom Stone Professor @Penn @PennEngineers @PennCIS @GRASPlabErik Meijer @headinthebox
27K Followers 0 FollowingKyle Beaudette @KyleBeautweet
14K Followers 734 Following Author/Illustrator of The Garden Witch coming this Fall! https://t.co/W0ty9QMtXvYaron Lipman @lipmanya
3K Followers 398 Following Faculty at @WeizmannScience, research scientist @MetaAI (FAIR). Interested in deep learning of irregular/geometric data and generative models.🎗️Dreaming Tulpa 🥓�.. @dreamingtulpa
34K Followers 1K Following Coder and AI whisperer | 🇨🇭 | @aiia_dao Keeping up to date with Generative AI on https://t.co/JjX7INV1K5 Building https://t.co/0tHHSgyHnn More here 👉 https://t.co/8ES5KiPMNDOliver Cameron @olivercameron
41K Followers 500 Following Building something new! Built self-driving cars at @cruise and @voyage. Board member at @skyways. @ycombinator alum. Angel investor in 60+ DeepTech startups.Detail @detailapp
2K Followers 113 Following The camera app for storytellers. Unleash your creativity with a powerful video app that combines recording and editing in one simple experience.Paul Veugen @pveugen
6K Followers 2K Following Building @detailapp. Share your story with video faster. Making video easier than text. Investor @nphardvc. Prev: Founder Usabilla & Human.Jerome Revaud @JeromeRevaud
1K Followers 96 Following AI researcher :: Computer vision :: 3D vision :: Team Lead :: Project Lead :: Naver Labs EuropeVincent Leroy @Vinc3nt_Leroy
312 Followers 37 Following Research scientist in Geometric deep learning, 3D vision and reconstruction.Ramin Hasani @ramin_m_h
3K Followers 256 Following Cofounder & CEO https://t.co/fh9fnDA9OQ | ML Researcher @ MITAaron Levie @levie
2.5M Followers 629 Following Lead Magician (and CEO) at Box (@box); Huge ABBA fan. I don't fully endorse anything I say below. Go ☁VantAI @vant_ai
993 Followers 3 Following Unlocking a new chapter in medicine by making protein interactions programmableTucker Carlson @TuckerCarlson
12.8M Followers 1 FollowingBrett Adcock @adcock_brett
171K Followers 14 Following Founder @Figure_robot (AI Robotics) & Archer Aviation (NYSE: ACHR)Corey Lynch @coreylynch
10K Followers 1K Following AI at @figure_robot, previously research scientist at @GoogleDeepMind.Trevor McCourt @trevormccrt1
9K Followers 265 Following CTO @Extropic_AI. PhD (ABD) + MSc @MITEECS + @MitQuanta + @FieteGroup. former @GoogleAI Quantum, former @UWaterloo Mechanical Engineering. opinions my ownMelanie Baldridge @recostseg
51K Followers 172 Following I help real estate investors defer taxes with Cost Segregation. Quick turnarounds with virtual visits and high-quality engineered reports.Latent Technology @L4tent
334 Followers 9 Following Building the next generation animation technology for virtual worlds using cutting-edge AI.Cognition @cognition_labs
123K Followers 19 Following Makers of Devin, the first AI software engineer. We are an applied AI lab focused on reasoning, and code is just the beginning. Join us: https://t.co/tpfZwEwGiqBarton Smith @bartonsmith
6K Followers 413 Following Gone independent with apps, products, furniture. Previously: @spotify, @fiftythree, @facebook, @fuseprojectMuchas felicidades a mi hijo Rafael por su premio a la excelencia académica en la facultad de derecho de la Universidad de Guanajuato!
Reconstructing Ignatius (Tanks&Temples) from 7,843 images, starting from raw images without intrinsics, in one hour on a V100. #ACEZero
Faster colmap MVS available from docker pull parskatt/colmap:12.2.2-sm_80
This is their “test prototype” they are showing off. It seems like they ripped my design files directly from here: hackaday.io/project/186410… And I’m 90% sure they’re using my software to fly this thing too. It flies with all the same little quirks I’d expect from my code.
Alright Twitter, how petty should I get over on LinkedIn, on a scale of 1-10? Newly unveiled revolutionary, groundbreaking, and 100% original drone design announced today!
While waiting for the open source approval, we have upgraded VGGSfM from v1 to v1.1. The new one is much more accurate, particularly with strict thresholds such as AUC@3. Additionally, it's twice faster during inference. @davnov134 @chrirupp @n_karaev
@WayneINR @AjdDavison @LourdesAgapito Here are the slides of my recent invited talk about CroCo + DUSt3R + MASt3R files.europe.naverlabs.com/index.php/file… Note: It's a pdf, i know the videos won't work but there's really nothing hitherto unseen. I can point to where to find each individual video upon request.
@AjdDavison Same goes in the other direction. I wasn’t expecting that many excellent, really top-notch papers and demos. Super interesting research overall! Also really liked the atmosphere in your lab, for sure one of the best lab i visited
I just updated my Meta glasses and it does everything I see Humane users wanting the Ai Pin to do. Low latency Multimodal works flawlessly Everything **just works** on my $299 glasses with no subscription @MKBHD didn’t kill Humane, Zuck did 😂
Meta's Ray-Ban glasses now have multimodal AI
📢 Code release for 𝗗𝗦𝗜𝗡𝗘 (#CVPR2024 - Oral) DSINE gives you surface normal prediction (+ uncertainty) in real-time. We have released the code for training, testing, and running real-time demos. Try it yourself! github.com/baegwangbin/DS…
A lens that brings objects back to an 8-bit status [🔍 Hakusi_Katei]
Working moderately hard over long periods of time will take you much further than getting overexcited, trading your long-term health against short-term results, and burning out. Play the long-term game, that’s the only game that matters.
With satellite imagery, it’s hard to get labels. Solution? DINOv2! WRI+Meta trained a satellite DINOv2 for tree height estimation. They created an interactive map of tree height of the whole globe (!) at 1-meter res (!): …toring-okw37.projects.earthengine.app/view/canopyhei… Quizz: Can you recognize this city?
Ray-Ban Meta smart glasses just got a massive Multimodal upgrade - Meta AI with Vision It doesn't just take speech input, it can now answer questions about what you are seeing. Here are 8 features that is now possible 1. Ask about what you are seeing
Thanks for sharing :) TLDR: Introducing an image evaluation method that assesses rendered images via images from other viewpoints, eliminating the need for ground truth. Primary use: assessing novel views in NVS tasks. ⛳️ crossscore.active.vision 📄 arxiv.org/abs/2404.14409
CrossScore: Towards Multi-View Image Evaluation and Scoring @ziruiwang_, @wenjing_bian, @omkarparkhi, @CarlYuhengRen, @viprad tl;dr: cross-attention+data from NVS optimisation->compare query image and multiple views of the same scene->IQA without GT arxiv.org/pdf/2404.14409…
FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent arxiv.org/abs/2404.15259 Project: cameronosmith.github.io/flowmap/
Coming back from London, after being kindly invited for a talk about DUSt3R + MASt3R in the Dyson lab of @AjdDavison at Imperial college and in the 3DV team of @LourdesAgapito at UCL. Had insightful discussions with all lab’s members, this was truly a great time spent there ❤️
📢📢📢 𝐁𝐀𝐍𝐅: 𝐁𝐚𝐧𝐝-𝐥𝐢𝐦𝐢𝐭𝐞𝐝 𝐍𝐞𝐮𝐫𝐚𝐥 𝐅𝐢𝐞𝐥𝐝𝐬 𝐟𝐨𝐫 𝐋𝐞𝐯𝐞𝐥𝐬 𝐨𝐟 𝐃𝐞𝐭𝐚𝐢𝐥 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 lead by Ahan Shabanov (@ahan_sh) at #CVPR2024 Wonder how to get frequency control in neural fields? This is for you: theialab.github.io/banf