nermin samet (@nemka_) header
nermin samet (@nemka_) profile picture

Research Scientist at @valeoai | Previously postdoc at @ImagineEnpc, PhD in Computer Vision @metu_imagelab. I love Computer Vision and Soft Pastels.

Paris, France
Joined November 2010
Photo by nermin samet (@nemka_)
1/n Our paper REPA-G is accepted at #NeurIPS2026! 🎉 I'll present it at the NeurIPS Paris site 🇫🇷. We introduce test-time conditioning of REPA-style diffusion models with visual features, with no extra training.
3
25
119
5,761
nermin samet retweeted
a bit confused about the NeurIPS site assignment. we chose Paris but got Atlanta because Paris was full. all authors are based in Europe and don’t plan to travel to the US. if we can just be assigned elsewhere, what was the point of choosing a site? and what was the point of @EurIPSConf?
2
4
1
82
26,127
Come see our poster tomorrow afternoon at #ICRA2026 to talk about 3D representation alignment of diffusion models for LiDAR generation. 📍196, Hall C 🗓️ Wednesday, 3:00-4:30 PM
📢 New preprint! We introduce R3DPA - a LiDAR scene generator that: • Transfers RGB-pretrained generative priors to 3D • Aligns with self-supervised LiDAR features • Enables object inpainting & scene mixing at inference • Sets SOTA on KITTI-360
5
1
7
1,096
nermin samet retweeted
LOSC: LiDAR Open-voc Segmentation Consolidator 🚨oral🚨 tl;dr: 1) projecting 2D VLM predictions into 3D space + 2) refining w/ spatio-temp. and augmentation consistency --> 3) train a robust 3D network. by @nemka_, @gillespuy, and R. Marlet 📜 arxiv.org/abs/2507.07605 💻✅
1
2
314
1/ 📢 New preprint: Test-Time Conditioning with Representation-Aligned Visual Features Introducing REPA-G — a framework for controllable image generation at inference time using aligned visual features. 📄 arxiv.org/pdf/2602.03753 💻 github.com/valeoai/REPA-G 🧵👇
1
19
1
90
5,342
1/🧵 Q: Can we have both a simple and SOTA architecture in autonomous driving? R: Yes! 😍 Introducing Driving on Registers (DrivoR): a pure Transformer backbone that achieves SOTA results in NAVSIM v1 / v2 and closed-loop HUGSIM evaluation. Here is how 👇
1
12
4
28
12,389
If you are interested in 3D or LiDAR generation, come check out our poster (with @Mickael_Chen @nemka_ and Renaud Marlet) this afternoon (ses. 2) LOGen: Toward Lidar Object Generation by Point Diffusion arxiv.org/abs/2412.07385 fully open sourced here: github.com/valeoai/LOGen
3
1
11
1,097
nermin samet retweeted
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation by @ccrommel, @VLetzelter, @nemka_, R. Marlet, @quobbe, @ptrkprz, E.Valle tl;dr: a new method and metrics for circumventing topology inconsistency issues via constrained multiple hypotheses #NeurIPS2024
1
2
3
324
nermin samet retweeted
We'll be ✈️@CVPR next week with lots of exciting things to present! Find a summary below and do come to say Hi and chat with us at the posters #CVPR2024 👇
Super excited to be ✈️@CVPR next week to present our recent works. On the menu: images, point clouds, and language in generative, distillation, self-supervised, sparse, forecasting, generalization, and unsupervised settings... Find out more 👇 and come meet us at #CVPR2024
2
18
2,498
🚨What about doing 3D pose estimation, but with the 133 keypoints of the COCO whole-body layout? We have a cool poster with Yue Zhu and @nemka_ Friday PM at N018. I'll show the many good tricks in the long 🧵 below. 💻github.com/wholebody3d/whole… 📜openaccess.thecvf.com/conten… 1/12
1
3
1
28
26,096
nermin samet retweeted
Find out more about SeedAL: smarter active learning for point clouds using image foundation models this Fri AM poster #081 Sud @nemka_ @gillespuy @oriane_simeoni will be there #ICCV2023
Replying to @valeoai
You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation @nemka_ @oriane_simeoni @gillespuy G.Ponimatkin R.Marlet @VincentLepetit2 tl;dr: kickstart active learning w/ image features #ICCV2023 pdf: arxiv.org/abs/2304.11762
2
1
11
1,526
nermin samet retweeted
You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation @nemka_ @oriane_simeoni @gillespuy G.Ponimatkin R.Marlet @VincentLepetit2 tl;dr: kickstart active learning w/ image features #ICCV2023 pdf: arxiv.org/abs/2304.11762
1
4
1
12
2,774
#ICCV2023 Fri Oct 6 (PM) H3WB: Human3.6M 3D WholeBody Dataset and Benchmark Yue Zhu, @nemka_, @david_picard pdf: arxiv.org/abs/2211.15692 code: github.com/wholebody3d/whole…
1
1
13
883
#ICCV2023 Fri Oct 6 (AM) You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation @nemka_, @oriane_simeoni, @gillespuy, G. Ponimatkin, R. Marlet, @VincentLepetit2 pdf: arxiv.org/abs/2304.11762 code: github.com/nerminsamet/seeda…
1
2
16
977
nermin samet retweeted
#WACV2023 A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation Georgy Ponimatkin, @nemka_, Yang Xiao, @Yuming Du, Renaud Marlet, @VincentLepetit2; pdf: arxiv.org/abs/2209.09341 web: ponimatkin.github.io/ssl-vos… code: github.com/ponimatkin/ssl-vo…
1
2
7
2,308
"HoughNet: Integrating Near and Long-Range Evidence for Visual Detection" by @nemka_ , @giddyyupp and @eakbas2 has been accepted to IEEE TPAMI! Paper: ieeexplore.ieee.org/document… Code: github.com/nerminsamet/hough…
7
19
Come and join us at the Women in Computer Vision workshop happening now! @WiCVworkshop #CVPR2021
Calling all allies to join us at the Women in Computer Vision workshop happening now @ #CVPR2021. Hear from early career researchers & provide your feedback. You can engage w/ oral speakers and poster presenters sharing their work. Learn about them here: sites.google.com/view/wicvcv…
1
11
nermin samet retweeted
With the generous funding received from our sponsors, we are happy to offer extra spots for WiCV workshop in the upcoming CVPR. Please fill out this form latest by Jun 18th to be considered for the conference registration funding: forms.gle/Z4BZk3fqrAC2e3Cg6
1
10
7
21
nermin samet retweeted
We are very excited to share the second fully virtual Women in Computer Vision workshop as part of CVPR 2021 is happening on Saturday June 19. Thanks to our sponsors, participants, and volunteers, we have a full schedule of invited talks, a panel discussion, and mentoring session
1
32
2
98
nermin samet retweeted
Submission deadline has been extended to 19th of March for 9th Women in Computer Vision Workshop (WiCV) at #CVPR2021 sites.google.com/view/wicvcv…
8
2
26