DUSt3R et al. are impressive, but how do they actually work? We investigate this in our project ๐๐ฏ๐ฅ๐ฆ๐ณ๐ด๐ต๐ข๐ฏ๐ฅ๐ช๐ฏ๐จ ๐๐ถ๐ญ๐ต๐ช-๐๐ช๐ฆ๐ธ ๐๐ณ๐ข๐ฏ๐ด๐ง๐ฐ๐ณ๐ฎ๐ฆ๐ณ๐ด!โฃ
We share findings on the iterative nature of reconstruction, the roles of cross and self-attention, and the emergence of correspondences across the network [1/8] โฌ๏ธ
04.11.2025 19:40 โ ๐ 5 ๐ 3 ๐ฌ 1 ๐ 0
xfactor!!
07.11.2025 03:48 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
It seems like back in the 2000s, while arxiv did exist, most CS researchers would just host their preprints on their personal sites. But now in ML, putting your paper on arxiv seems like a must. What do you think changed? Could this policy mean the return of self-hosted preprints?
04.11.2025 00:41 โ ๐ 1 ๐ 0 ๐ฌ 1 ๐ 0
Curated Data for Efficient Learning
The ICCV 2025 Workshop on Curated Data for Efficient Learning
Our schedule is live!
curateddata.github.io/schedule.html
We have posters, oral presentations, and invited talks from @zhuangl.bsky.social, @sarameghanbeery.bsky.social, @andrewowens.bsky.social, @phillipisola.bsky.social, and Alyosha Efros!
See you in Hawaii!
#ICCV2025 @iccv.bsky.social
12.10.2025 21:26 โ ๐ 9 ๐ 3 ๐ฌ 0 ๐ 1
Come see our talk on "Pocket Time-Lapse" at SIGGRAPH today at 4pm in the Image Representation, Editing, & Generation session!
West Building, Rooms 118-120
13.08.2025 08:39 โ ๐ 4 ๐ 1 ๐ฌ 0 ๐ 0
3D render of dogs on skateboards
Congrats, love this figure!
05.08.2025 16:09 โ ๐ 4 ๐ 0 ๐ฌ 1 ๐ 0
Excited to share our new work at @acm.org Transactions on Graphics/@acmsiggraph.bsky.social! We use coded noise to add an invisible watermark to lighting that helps detect fake or manipulated video. (1/2)
30.07.2025 15:56 โ ๐ 10 ๐ 3 ๐ฌ 1 ๐ 0
At ICML, we're presenting a paper on uncertainty-aware surface reconstruction!
Compared to previous approaches, we are able to completely remove the need for recursive linear solves for reconstruction and interpolation, using geometric GP machinery.
Check it out!
17.07.2025 18:24 โ ๐ 10 ๐ 3 ๐ฌ 1 ๐ 0
๐จ๐จ WiGRAPH CONFERENCE COFFEE @ SIGGRAPH '25 ๐จ๐จ
Sign up now to be randomly matched with peers for a SIGGRAPH conference coffee!
10.07.2025 16:39 โ ๐ 9 ๐ 4 ๐ฌ 0 ๐ 0
๐ข I'm excited to share BrepDiff, our single-stage B-rep diffusion model, which enables unconditional generation and editing of B-reps.
This work will be presented at #SIGGRAPH2025 with @mingilikesmangos.bsky.social, @dongsuzhang.bsky.social, and Young Min Kim.
๐: brepdiff.github.io
1/8
30.06.2025 14:35 โ ๐ 10 ๐ 3 ๐ฌ 1 ๐ 1
I think it often refers to parameterizing a camera's ray bundle with Plucker coordinates
04.04.2025 05:17 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
The multi-plane camera at the Walt Disney Family museum. Itโs huge!
24.03.2025 23:41 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
Incoming Assistant Professor @cornellbowers.bsky.social
Researcher @togetherai.bsky.social
Previously @stanfordnlp.bsky.social @ai2.bsky.social @msftresearch.bsky.social
https://katezhou.github.io/
Mayor-Elect of New York City
PhD student at รcole Polytechnique
Interested in Computer Vision, Geometry, and learning both at the same time
https://www.jgaubil.com/
Professor at NYU; Scientific Director at Ctr for Computational Neurocience, Flatiron Institute. Research in Computational Vision (neurons, perception, machines). Opinions my own.
Official account for the IEEE/CVF International Conference on Computer Vision. #ICCV2025 Honolulu ๐บ๐ธ Co-hosted by @natanielruiz @antoninofurnari @yaelvinker @CSProfKGD
The First Workshop on Curated Data for Efficient Learning @ ICCV'25
Assistant Professor of Computer Science at the University of British Columbia. I also post my daily finds on arxiv.
https://bettercities.substack.com/
Better cities and transit are possible ๐
#1 Congestion pricing stan
#1 RFK Jr. hater
Assistant Professor @UWaterloo CS
rendering, light transport & optics
PhD @UCSB, MSc @WeizmannScience, formerly @Crytek @NVIDIA.
๐ฎ๐ฑ๐จ๐ฆโก๏ธ
ssteinberg.xyz
Language processing - Neuroscience - Machine Learning - Assistant Professor at Stanford University - She/Her - ๐ณ๏ธโ๐
Computer Graphics PhD student at TU Berlin.
(differentiable) rendering, inverse graphics, GPGPU
mworchel.github.io
PhD @Berkeley prev CS/Math @MIT
Blog: https://argmin.substack.com/
Webpage: https://people.eecs.berkeley.edu/~brecht/
Graphics researcher at TU Delft. Formerly Intel, KIT, NVIDIA, Uni Bonn. Known for moment shadow maps, MBOIT, blue noise, spectra, light sampling. Opinions are my own.
https://MomentsInGraphics.de
Computer Vision & Machine Learning
๐ Pioneer Centre for AI, University of Copenhagen
๐ https://www.belongielab.org
Director, MIT Computational Psycholinguistics Lab. President, Cognitive Science Society. Chair of the MIT Faculty. Open access & open science advocate. He.
Lab webpage: http://cpl.mit.edu/
Personal webpage: https://www.mit.edu/~rplevy
3D geometry researcher: graphics, vision, 3D ML, etc | Senior Research Scientist @NVIDIA | polyscope.run and geometry-central.net | running, hockey, baking, & cheesy sci fi | opinions my own | he/him
personal website: nmwsharp.com
Postdoc @ UC Berkeley. 3D Vision/Graphics/Robotics. Prev: CS PhD @ Stanford.
janehwu.github.io
Computer Vision & Machine Learning researcher at NAVER LABS europe
she/her - https://dlarlus.github.io/
PhD in Applied Physics from Cornell, with specialization in micro/nano fabrication and computational origami
Helping spread Veritasium, Stand-up Maths, and Steve Mould into China
