Edgar Sucar (@sucaredgar) 's Twitter Profile
Edgar Sucar

@sucaredgar

Postdoc @Oxford_VGG |
PhD Dyson Robotics Lab at Imperial College

ID: 858493718952804352

linkhttp://edgarsucar.github.io calendar_today30-04-2017 01:30:27

110 Tweet

718 Followers

1,1K Following

Alexandre Morgand (@almorgand) 's Twitter Profile Photo

Glad to see Edgar Sucar, Andrew Davison "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/

Glad to see <a href="/SucarEdgar/">Edgar Sucar</a>, <a href="/AjdDavison/">Andrew Davison</a> "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/
Luca Carlone (@lucacarlone1) 's Twitter Profile Photo

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

Dmitrii Tochilkin (@cut_pow) 's Twitter Profile Photo

"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

Andrew Davison (@ajddavison) 's Twitter Profile Photo

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…

Andrew Davison (@ajddavison) 's Twitter Profile Photo

#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! Iain Haughton et al, Dyson Imperial Computing. Paper/video: ihaughton.github.io/RobE/

Andrew Davison (@ajddavison) 's Twitter Profile Photo

If you're at CORL this week in NZ come and meet Iain Haughton and Edward 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.

Kirill Mazur (@makezur) 's Twitter Profile Photo

Our work on leveraging general pre-trained feature extractors for open-set real-time scene understanding has been accepted for #ICRA2023! Joint work with Edgar Sucar Andrew Davison Check out project page: makezur.github.io/FeatureRealist…

Stephen Wolfram (@stephen_wolfram) 's Twitter Profile Photo

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…

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…
Eric Dexheimer (@eric_dexheimer) 's Twitter Profile Photo

Excited to announce "Learning a Depth Covariance Function" with Andrew Davison. 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

Xin Kong (@xinkong_ic) 's Twitter Profile Photo

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, Shikun Liu, Marwan Taher, Andrew Davison.

Andrew Davison (@ajddavison) 's Twitter Profile Photo

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.

Anagh Malik (@anagh_malik) 's Twitter Profile Photo

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

José M. Carranza (@josemtzcarranza) 's Twitter Profile Photo

Among the keynote speakers, we had two great keynotes delivered by young researchers: Dr. Saiph Savage Dra. Saiph Savage and Dr. Edgar Sucar Edgar Sucar , who besides being excellent researchers, are proudly Mexican!

Among the keynote speakers, we had two great keynotes delivered by young researchers: Dr. Saiph Savage <a href="/saiphcita/">Dra. Saiph Savage</a> and Dr. Edgar Sucar <a href="/SucarEdgar/">Edgar Sucar</a> , who besides being excellent researchers, are proudly Mexican!
Edgar Sucar (@sucaredgar) 's Twitter Profile Photo

SLAM bitter lesson: methods that do less “test time optimisation” will eventually trump over the methods that do more .

Edgar Sucar (@sucaredgar) 's Twitter Profile Photo

Good essay on the analogy of the stone soup tale to AI misconception. More emphasis is placed on individual AI models and teams/algorithms who made them, rather than on the collective effort to generate big data, the most important ingredient of the soup. simons.berkeley.edu/news/stone-sou…