François Rameau retweeted
Behind every academic program are decisions about what to teach and which ideas to prioritize.
Our General Chairs have spent months shaping the ANAIS 2026 program. The schedule is now live!
🔗 anais.naamii.org.np/program
Applications open: anais.naamii.org.np/
#ANAIS2026
François Rameau retweeted
Recommendation notifications for #3DV2027 are going out by the end of the day (AoE). We’re waiting on a few final meta-reviews.
In case you’re worried about your rebuttal time, author feedback is postponed to November 2 (AoE).
Thanks for your patience!
François Rameau retweeted
🍯 Got exciting 3D vision work that deserves another spotlight -- or a bold idea that isn’t quite a paper yet?
Then the #3DV2027 Nectar Track is for you: showcase strong recent work, share early ideas and demos; all while enjoying bougatsa, meze, and rebetiko in beautiful Thessaloniki 🇬🇷
📅 Deadline: Feb 15, 2027 (more details coming soon)
👉 3dvconf.github.io/2027/call-…
François Rameau retweeted
Happy to announce our #ECCV2026 long Oral paper, Poppy, on using polarization of light to enhance monocular 3D estimation at test time. 🌺
irnkim.github.io/poppy
Kudos to Irene Kim and the team, Sai Tanmay Reddy Chakkera, Alexandros Graikos, and Dimitris Samaras
(Thread 👇)
François Rameau retweeted
Next stop #ECCV2026 Malmö, Sweden 🇸🇪
Conference page: eccv.ecva.net/Conferences/20…
François Rameau retweeted
I'm particularly excited by Atlas's ability to reconstruct scenes from a very small number of input image -- was able to create this flythrough of London's Natural History Museum by combining 3 input images I found from completely separate sources on Google Images
François Rameau retweeted
Excited to announce MC-Calib v1.5.0!
By upgrading to OpenCV 5, reprojection errors are almost halved across all tested scenarios.
Shoutout to @LearnOpenCV for encouraging the upgrade.
🔗 github.org/rameau-fr/MC-Cali…
MC-Calib: a generic and robust calibration toolbox for multi-camera systems
TLDR: open source to calibrate multi-camera (perspective, fisheye, hybrid) systems with diverse configurations (overlapping, non-overlapping, converging).
GitHub: github.com/rameau-fr/MC-Cali…
François Rameau retweeted
We are happy to announce that our paper on Immediate3DGS will be presented at SIGGRAPH! This work was conducted with @_linus_franke, Boris Zhestiankin, @cammonteCG, and @GDrettakis.
1/4
François Rameau retweeted
We are recruiting multiple postdocs at Oxford:
cs.ox.ac.uk/news/2520-full.h…
François Rameau retweeted
I tried to explain @ylecun in a new way in this video. How Nature Solved Robotics. Full video link 👇
François Rameau retweeted
Looking for a nice home for your paper? #3DV2027 is waiting! 🎉
⏰ Conference dates: April 6-9, 2027
✈️ Place: #Thessaloniki (#SKG), #Greece 🇬🇷
📝 Paper ddl: Aug 28
🎥 Supp ddl: Sep 02
🆕 Rebuttal only upon invite for borderline papers!
#CallForPapers: 3dvconf.github.io/2027/call-…
François Rameau retweeted
The deadline for submitting #ECCV2026 final reviews is TODAY! Please act responsibly and finalize your discussions and reviews.
We are grateful to all of the 17,491 reviewers who helped make #CVPR2026 possible. We are especially pleased to recognize the following Outstanding Reviewers, whose high-quality reviews (as judged by their Area Chairs) placed them among the top 5% of reviewers.
François Rameau retweeted
Pixel-Accurate Epipolar Guided Matching
Oleksii Nasypanyi, Francois Rameau
tl;dr: tolerance circle->keypoint->an angular interval->contain the epipolar line direction->1D angular interval query->matching
arxiv.org/abs/2603.18401



































