Philipp Lindenberger

12 posts

Philipp Lindenberger

Philipp Lindenberger

@PhilippCSE

PhD student in the Computer Vision and Geometry Group, ETH Zürich

Zurich, Switzerland Entrou em Ekim 2013
133 Seguindo224 Seguidores
Philipp Lindenberger retweetou
Elisabetta Fedele
Elisabetta Fedele@efedele16·
The submissions to our @CVPR workshop OpenSUN3D on Open-World 3D Scene Understanding and Representations are open! 🏔️🤖☀️ ➡️ The deadline for the proceedings track is on the 5th of March!🏃‍♀️ 🌍: opensun3d.github.io 📝: openreview.net/group?id=thecv…
Elisabetta Fedele tweet media
English
1
11
34
15.1K
Philipp Lindenberger
Philipp Lindenberger@PhilippCSE·
We propose to tackle this problem by fusing two popular research branches: direct image geo-localization via classification, and cross-view retrieval against aerial imagery. We show that these tasks not only synergize, but eliminate fundamental limitations of the other approach.
Philipp Lindenberger tweet media
English
0
0
4
133
Philipp Lindenberger retweetou
Dmytro Mishkin 🇺🇦
Dmytro Mishkin 🇺🇦@ducha_aiki·
Some benchmark of the modern local features with LightGlue on #IMC2021 dataset. 0) Use ALIKED features. 1) ALIKED 2k is on par with other features 8k 2) DISK overfits to buildings 3) DoG detector benefits from 8k the most
Dmytro Mishkin 🇺🇦 tweet mediaDmytro Mishkin 🇺🇦 tweet mediaDmytro Mishkin 🇺🇦 tweet mediaDmytro Mishkin 🇺🇦 tweet media
English
2
4
20
3.9K
Philipp Lindenberger
Philipp Lindenberger@PhilippCSE·
@ducha_aiki Thank you for this great blog post! We also observed this phenomenon, and my best guess is that the spatial distribution of matched points and noisy pose estimation perturb the results. However, we found that non-linear pose refinement (e.g. with PoseLib) reduced this error.
English
0
0
2
127
Dmytro Mishkin 🇺🇦
Dmytro Mishkin 🇺🇦@ducha_aiki·
@PhilippCSE do you have any idea (except possible overfitting), why match recall/precision could be not correlated with pose accuracy?
English
1
0
2
1K
Dmytro Mishkin 🇺🇦
Dmytro Mishkin 🇺🇦@ducha_aiki·
New post in my WxBS blog: Experiments with LightGlue: geometry representation and initialization. - Does it matter how you provide additional geometry info (scale, orientation for SIFT) to LightGlue? - Can we tune existing LightGlue for new features? ducha-aiki.github.io/wide-baseline-…
English
3
10
45
7.4K
Philipp Lindenberger retweetou
Paul-Edouard Sarlin
Paul-Edouard Sarlin@pesarlin·
📢Join us tomorrow Friday morning at our #ICCV2023 poster S-6 to learn more about LightGlue! 💥We have released the training code at github.com/cvg/glue-facto… ➡️You can now train LightGlue with SIFT, ALIKED, or your own local features, on your own dataset ⏩More models coming soon!
Paul-Edouard Sarlin@pesarlin

You liked SuperGlue? You'll love ⚡️LightGlue⚡️, our new deep network for light-speed image matching! ➡️Faster, stronger, easier to train than SuperGlue ➡️Code: github.com/cvg/LightGlue ➡️Paper: arxiv.org/pdf/2306.13643… Fantastic work by @PhilippCSE for #ICCV2023, with @mapo1 1/

English
2
11
100
11.8K
Philipp Lindenberger retweetou
ICCV2021
ICCV2021@ICCV_2021·
Best Student Paper @ICCV_2021 Pixel-Perfect Structure-from-Motion with Featuremetric Refinement Philipp Lindenberger (ETH Zurich), Paul-Edouard Sarlin (ETH Zurich), Viktor Larsson, Marc Pollefeys [Session 5 A/B]
English
1
9
58
0