iiinova — where your digital self keeps evolving

Torsten Sattler @sattlertorsten.bsky.social · 27/06/2025

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

062

Torsten Sattler @sattlertorsten.bsky.social · 19/06/2025

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

140

Torsten Sattler @sattlertorsten.bsky.social · 12/06/2025

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 ;)

0169

Torsten Sattler @sattlertorsten.bsky.social · 12/06/2025

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

090

Torsten Sattler @sattlertorsten.bsky.social · 29/05/2025

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.

000

Torsten Sattler @sattlertorsten.bsky.social · 27/05/2025

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

020

Torsten Sattler @sattlertorsten.bsky.social · 27/05/2025

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).

130

Torsten Sattler @sattlertorsten.bsky.social · 27/05/2025

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...

sites.google.com

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...

22410

Reposted by Torsten Sattler

Eric Brachmann @ericbrachmann.bsky.social · 15/01/2025

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

1307

Torsten Sattler @sattlertorsten.bsky.social · 15/01/2025

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.

2293

Torsten Sattler @sattlertorsten.bsky.social · 15/01/2025

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.

190

Torsten Sattler @sattlertorsten.bsky.social · 15/01/2025

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.

1100

Torsten Sattler @sattlertorsten.bsky.social · 27/12/2024

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

110

Reposted by Torsten Sattler

Eric Brachmann @ericbrachmann.bsky.social · 04/12/2024

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...

nianticlabs.com

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

2397

Torsten Sattler @sattlertorsten.bsky.social · 29/11/2024

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

010

Torsten Sattler @sattlertorsten.bsky.social · 29/11/2024

... 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.

020

Torsten Sattler @sattlertorsten.bsky.social · 29/11/2024

... 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

110

Torsten Sattler @sattlertorsten.bsky.social · 29/11/2024

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 ...

110

Torsten Sattler @sattlertorsten.bsky.social · 29/11/2024

... 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

270

Torsten Sattler @sattlertorsten.bsky.social · 29/11/2024

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 ...

140

Torsten Sattler @sattlertorsten.bsky.social · 26/11/2024

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.

110

Torsten Sattler @sattlertorsten.bsky.social · 26/11/2024

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.

000

Torsten Sattler @sattlertorsten.bsky.social · 26/11/2024

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.

000

Torsten Sattler @sattlertorsten.bsky.social · 26/11/2024

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

140

Torsten Sattler @sattlertorsten.bsky.social · 25/11/2024

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

120

Torsten Sattler @sattlertorsten.bsky.social · 25/11/2024

... getting good reviewers often means getting a good AC who is familiar with the field and know the right people to review the paper. Getting a good AC often means the PCs doing a good job with assigning papers to ACs. All parts of the chain are important.

110

Torsten Sattler @sattlertorsten.bsky.social · 25/11/2024

... decisions) can certainly be made easier (e.g., don't require meta reviews for clear cases), but can't be fully automated. I don't think we can automate anything close to 90%. I agree that getting good reviewers (knowledgeable about the field, willing to put in work) is important. But ...

automated.in

Domain Details Page

110

Torsten Sattler @sattlertorsten.bsky.social · 25/11/2024

I tend to (partially) disagree. The only part that could currently be automated is sending reminders (in my experience, people are more likely to respond to personalized requests). The other parts (assigning reviewers, leading discussions, checking reviews & rebuttals, justifying and checking ...

110