Lightnews — Scholar-powered news

Torsten Sattler @sattlertorsten.bsky.social · Jun 27

We have extended the deadline for paper submissions to July 1st.

Torsten Sattler @sattlertorsten.bsky.social · May 27

Working on camera calibration or camera pose estimation? Want to finally know how calibrations and poses are obtained for the data you ae using?
Come join us at the CALIPOSE workshop at @iccv.bsky.social

Details are on the workshop website: sites.google.com/view/calipos...

Camera Calibration and Pose Estimation (CALIPOSE)

Workshop Information When: October 19th or 20th, 2025 Where: Honolulu, Hawai'i, ICCV 2025 Time: TBD Preliminary Schedule Opening [all organizers, 5 mins] Invited Talk I: Richard Hartley [30 mins] Inv...

sites.google.com

2 6

Torsten Sattler @sattlertorsten.bsky.social · Jun 19

This is consistent with what we observed when we did the same experiment for ECCV 2024.

1 4

Torsten Sattler @sattlertorsten.bsky.social · Jun 12

Attending @cvprconference.bsky.social and looking for a PhD or postdoc position in the area of 3d reconstruction (Gaussian splatting, nerfs, scene understanding, etc.)? Find me or drop me an email ;)

10 17

Torsten Sattler @sattlertorsten.bsky.social · Jun 12

Come to our poster and learn about our working privacy-preserving localization.

Gabriela Csurka @gabrielacsurka.bsky.social · Jun 12

Excited to share Maxime’s latest work on Privacy Preserving Visual Localization. If interested Maxime will present his work tomorrow at #CVPR2025, Poster Session 1, Poster Number 85 (ExHall D).

10

Torsten Sattler @sattlertorsten.bsky.social · May 29

Yes, this is not yet decided and will, among others, depend on ICCV's policy on streaming / recording workshops and the technical equipment we will have.

Torsten Sattler @sattlertorsten.bsky.social · May 27

The workshop is organized by Zuzana Kukelova, Gabriella Flood, Viktor Larsson, Akihiro Sugimoto, and myself.

2

Torsten Sattler @sattlertorsten.bsky.social · May 27

We accept paper submissions on topics related to calibration and pose estimation, with a deadline on June 28th. See the website for a call for papers.
We also have exciting invited speakers (Richard Hartley, Eric Brachmann, Gabriela Csurka, Fredrik Kahl).

1 3

Torsten Sattler @sattlertorsten.bsky.social · May 27

Working on camera calibration or camera pose estimation? Want to finally know how calibrations and poses are obtained for the data you ae using?
Come join us at the CALIPOSE workshop at @iccv.bsky.social

Details are on the workshop website: sites.google.com/view/calipos...

Camera Calibration and Pose Estimation (CALIPOSE)

Workshop Information When: October 19th or 20th, 2025 Where: Honolulu, Hawai'i, ICCV 2025 Time: TBD Preliminary Schedule Opening [all organizers, 5 mins] Invited Talk I: Richard Hartley [30 mins] Inv...

sites.google.com

2 10 26

Reposted by Torsten Sattler

Eric Brachmann @ericbrachmann.bsky.social · Jan 15

I guess it has to be repeated for each new reviewing round: "See weaknesses" is not a justification of a review rating. And certainly not informative regarding what the authors should focus on in the rebuttal. #CVPR2025

1 7 30

Torsten Sattler @sattlertorsten.bsky.social · Jan 15

That is to say, I think it makes not much sense to fear what others might do. Do the research that you are interested in and I am sure it will be relevant as you bring a unique perspective to the field.

2 3 29

Torsten Sattler @sattlertorsten.bsky.social · Jan 15

Regarding progress in a field: I feel that a large part of the community is nomadic in the sense that they move from one area to another. E.g., there was a big rush on NeRFs, which has largely died down. Many seem to move on once the low-hanging fruits have been taken.

1 9

Torsten Sattler @sattlertorsten.bsky.social · Jan 15

I think you are selling yourself very short here. Don't think you would be irrelevant anywhere. Being in a place where you are happy and comfortable is very important. Also, Turkey seems to produce great researchers, so it seems like a good place to be.

1 10

Torsten Sattler @sattlertorsten.bsky.social · Dec 27

Maybe an issue of having enough training data? GANs can work reasonably well with rather limited data.

1 1

Reposted by Torsten Sattler

Eric Brachmann @ericbrachmann.bsky.social · Dec 4

Niantic is looking for research interns for next summer in London. Interested in the next generation of reconstruction, mapping and visual relocalization? Apply! (And send me a DM for good measure). Let's explore what the bitter-sweet lesson can do for 3D vision.

nianticlabs.com/careers/open...

2025 R&D Software Engineering Intern (PhD, Publishing) – Careers – Niantic Labs

nianticlabs.com

2 7 39

Torsten Sattler @sattlertorsten.bsky.social · Nov 29

Indeed, the original LO RANSAC paper (DAGM 2003) proposes multiple LO variants.

1

Torsten Sattler @sattlertorsten.bsky.social · Nov 29

... are nicely distributed over the images, you will likely get a better model than if all of them are in a small area in the images. In the latter case, the same level of correspondences noise has a much higher impact on model accuracy.

2

Torsten Sattler @sattlertorsten.bsky.social · Nov 29

... correspondences. Still, your model will have uncertainties, which (among potentially other things) depend on the inlier noise and the spatial configuration of the correspondences used to compute it. E.g., think of estimating the essential matrix from 20 correspondences. If these correspondences

1 1

Torsten Sattler @sattlertorsten.bsky.social · Nov 29

There multiple things here: a minimal solver will return an estimate that has 0 error on the correspondences in the minimal sample. Thus, the model will be noisy / have uncertainty. LO helps improve things by fitting the model to multiple data points, thus better accounting for noise in the ...

1 1

Torsten Sattler @sattlertorsten.bsky.social · Nov 29

... correspondences used to estimate the model) and the positions of the correspondences. See for examples this paper on handling uncertainty rahulraguram.com/assets/pdf/R... (a very good general treatment of uncertainties can be found in Wolfgang Fõrstner's book).

rahulraguram.com

2 7

Torsten Sattler @sattlertorsten.bsky.social · Nov 29

Assuming that you are fitting the "right" model (a model that can explain what you are observing), the optimal threshold not only depends the noise in the correspondences, but also on the uncertainty in the estimated model (which is a function of the inlier noise but also of the actual ...

1 4

Torsten Sattler @sattlertorsten.bsky.social · Nov 26

By the time that these decisions are made (you probably want to wait until you have the camera ready version), I'd assume that author identities are anyways known.

1 1

Torsten Sattler @sattlertorsten.bsky.social · Nov 26

Unfortunately, a too large part of the reviewer pool ignores almost all emails. Probably the only way to get their attention is to threaten with desk-rejects of their submissions, which seems a bit out of proportion.

Torsten Sattler @sattlertorsten.bsky.social · Nov 26

Indeed. CV conferences traditionally ask ACs to submit reviewer preferences. Certainly more work, especially since OpenReview and TPMS scores are not always reliable. Probably less chances for collusions than with reviewer bidding though.

Torsten Sattler @sattlertorsten.bsky.social · Nov 26

The common approach nowadays is that the program chairs make a shortlist of candidates (typically based on AC suggestions) and then select an independent committee (researchers without a conflict of interest with any of the papers) that decides the awards

1 4

Torsten Sattler @sattlertorsten.bsky.social · Nov 25

Ask a PhD student to search for the title on Google / Google Scholar / OpenReview and the authors' websites 😉

1 2