Linfei Pan

Ph.D. student in CVG @ETH Zurich

[Linfei Pan @LinfeiPan]

@surajhanchinal @YeheLiu That’s good news to hear already :)

[Linfei Pan @LinfeiPan]

@surajhanchinal @YeheLiu 12M means that there are a lot of images. In this case, I suggest you to just set an upper bound on the total number of tracks (controlled by some flag which is available in config) and give it a try again.

[Linfei Pan @LinfeiPan]

Heading to #CVPR2026 now 🚀 Looking forward to catching up with old friends and meeting new ones. Let me know if you’re around! 🤗✨

[Linfei Pan @LinfeiPan]

@anuragxel @ahojnnes @mapo1 We didn't test this variant, but results on ETH3D and IMC suggest SP/ALIKED + LG isn't necessarily more accurate (but they are more robust).

[Linfei Pan @LinfeiPan]

What if you could combine the precision of classical Structure-from-Motion with the local robustness of feedforward 3D models?

Meet GLUEMAP — a CVPR 2026 highlight ✨ SOTA across 5 datasets spanning 6 challenges.

w/ @ahojnnes & @mapo1

🌐website: https://t.co/pEh8jQh1ZN

[Linfei Pan @LinfeiPan]

@anuragxel @ahojnnes @mapo1 Thanks for your questions. a) Yes—with abundant features, SIFT still gives the best accuracy (see ablation in supp. mat.). b) Nice suggestion. We followed GLOMAP's protocol and target a more general unordered setup, but it's worth exploring in future work.

[Linfei Pan @LinfeiPan]

@zhenjun_zhao @ahojnnes @mapo1 Thanks for sharing our work!

[Linfei Pan @LinfeiPan]

@anuragxel @ahojnnes @mapo1 Thanks!

[Linfei Pan @LinfeiPan]

@CVPR Same question here: what should be put in the paper ID part exactly in this case?

[Linfei Pan @LinfeiPan]

It is presented at CVPR poster session 1 at stand 81 as a highlight paper. Look forward to feedbacks from the community!

[Linfei Pan @LinfeiPan]

📢 Introducing GenSfM – a generic Structure-from-Motion pipeline built on COLMAP, with smooth, invertible, and universal calibration for diverse cameras — from pinhole to catadioptric! Thanks @don2qian @visionviktor @mapo1 for the great collaboration.
🔗 https://t.co/Wa30YDf4vb

[Linfei Pan @LinfeiPan]

@mazy1998 @ChrisAtKIRI @don2qian @visionviktor @mapo1 thanks!

[Linfei Pan @LinfeiPan]

📢 Introducing GenSfM – a generic Structure-from-Motion pipeline built on COLMAP, with smooth, invertible, and universal calibration for diverse cameras — from pinhole to catadioptric! Thanks @don2qian @visionviktor @mapo1 for the great collaboration.
🔗 https://t.co/Wa30YDf4vb

[Zuri Bauer Hartwig @zuriich92]

🌺 Excited to announce the 1st CroCoDL Workshop on Large-Scale Cross-Device Localization at #ICCV2025!
Tackling real-world localization across smartphones, AR/VR, and robots with invited talks, paper track & competition on a novel dataset.

🔗 https://t.co/E41dLsdFvl

🧵 1/2

[Alejandro Fontán @AFontanVillcmp]

The Call for Papers is now open for our #RSS2025 workshop: Unifying Visual SLAM: From Fragmented Datasets to Scalable, Real-World Solutions

If you're working on #SLAM or #localization, we’d love to see your contributions!

https://t.co/7iA9EEMYhx

[Linfei Pan @LinfeiPan]

@ducha_aiki Hi, are you using Windows? Somehow windows can give this strange bug and we still haven’t figured out the reason😥. You can try limiting the maximum track number to potentially solve it (setting TrackEstablishment.max_num_tracks < 50k or so)

[Linfei Pan @LinfeiPan]

@pablovelagomez1 @majti89 @mapo1 @pesarlin thanks! Will look into it

[Linfei Pan @LinfeiPan]

@pablovelagomez1 @majti89 @mapo1 @pesarlin Hi, thanks for the effort. Do you mind sharing some of the mentioned failure cases of GLOMAP? Just for us to improve the library

[Xi @xiwang1212]

🚨 The CVG group at ETH Zurich is hiring! We are looking for PhD & PostDoc in egocentric vision and video understanding.

🔗 Apply by sending an e-mail to [email protected] and become part of our amazing team! @cvg_ethz @mapo1

[Linfei Pan @LinfeiPan]

@pablovelagomez1 @pesarlin @behnam_iut @janusch_patas No problem. I guess the gain for the global positioning would be similar to bundle adjustment but I would need to perform some tests to make an accurate conclusion there 😀

[Linfei Pan @LinfeiPan]

@pesarlin @pablovelagomez1 @behnam_iut @janusch_patas Yes, GLOMAP does not support GPU acceleration yet. The reason for re-implementing BA was the difference in the base classes. Global positioning is slightly different as it has many extra parameters. I guess both can potentially benefit from GPU.