Philipp Lindenberger

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

[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!🏃‍♀️

🌍: https://t.co/4nSXaJGNpR
📝: https://t.co/TYZKnuKeSo

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

RaCo: Ranking and Covariance for Practical Learned Keypoints

Abhiram Shenoi @PhilippCSE @pesarlin @mapo1

tl;dr: ALIKED arch + DaD RL training with full 360deg rotaug with detector+covariance heads, separate ranker (sorter) model . No IMC eval
#3DV2026
https://t.co/avrkyYFQ2L

[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 @PhilippCSE]

At #NeurIPS2025, we're presenting our work on Scaling Image Geo-Localization to Continent Level.

Website: https://t.co/vWCyOIuGiu
Paper: https://t.co/czDjRDJDUg

If you are at the conference, say 👋:
📍 Poster #4812, Dec 3 (Wed), 4:30–7:30 PM PST

[Philipp Lindenberger @PhilippCSE]

@ducha_aiki No worries, thank you for sharing our work :)

[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

[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.

[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 https://t.co/ZnKGFut80j
➡️You can now train LightGlue with SIFT, ALIKED, or your own local features, on your own dataset
⏩More models coming soon!

[Philipp Lindenberger @PhilippCSE]

@TobiasRobotics @condaforge @pesarlin @ducha_aiki @prefix_dev Very exciting to see pixsfm on @condaforge, thank you for this great contribution!

[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: https://t.co/SLLvKOwbEo
➡️Paper: https://t.co/8b38JCoFdg
Fantastic work by @PhilippCSE for #ICCV2023, with @mapo1
1/

[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]

[Paul-Edouard Sarlin @pesarlin]

🚨 This week at #ICCV2021, check out "Pixel-Perfect Structure-from-Motion with Featuremetric Refinement" w/ @PhilippCSE V. Larsson @mapo1
➡️ oral & *best student paper award*
Website: https://t.co/1QAdVO2A5y
Paper: https://t.co/ZL7qKT3UsE
Video: https://t.co/HwkfsSGGqx
thread ⬇️