Profile avatar
ericbrachmann.bsky.social
Staff Scientist at Niantic Throws machine learning at traditional computer vision pipelines to see what sticks. Differentiates the non-differentiable. http://ebrach.github.io
146 posts 1,771 followers 506 following
Regular Contributor
Active Commenter
Posts 14 Comments 36

Sometimes I wish I could adopt a Daniel Day-Lewis style to publishing. Write a good paper, retreat for several years to recover, repeat.

submitted 1 day ago • 1 comment

I lovehate deadline crunch time.

submitted 2 days ago • 0 comments

As an author, I had my fair share of reviewers explaining to us how our ideas were practically irrelevant. Even for papers that addressed a concrete business need. Some people really have a very narrow view coupled with over-confidence. It's ok to speak from your experience but keep it modest.

submitted 4 days ago • 1 comment

We created a new channel with daily new vision and graphics papers trending (liked/read) on www.scholar-inbox.com. This is the bsky equivalent of AK on X! Follow now, and never miss a beat again: bsky.app/profile/si-c...

submitted 7 days ago • 3 comments

🚨 Future open positions in AI at my home institution* targeted towards young researchers. These are tenure track positions with a good starting package, aimed at guiding you towards an ERC StG within 4 years. Feel free to contact me in DM. *ENPC, part of Institut Polytechnique de Paris

submitted 16 days ago • 0 comments

For PhD and MSc students interested in a research visit to Prague/VRG in 2025: we're open to hosting short-term collaborations or internships on a range of computer vision topics. If this sounds exciting, reach out by e-mail! We'd love to discuss potential projects. Some examples 🧵 #Internship #CV

submitted 16 days ago • 1 comment

Went through my #CVPR2025 batch again, and my reviewers did such a stellar job. Plenty of "exceeding expectations", not a single "below expectations", certainly no irresponsible reviewers. Informative reviews and active discussions everywhere. 😘 My hardest job as an AC is to parse all that info.

submitted 17 days ago • 0 comments

Looking for a distribution family for positively skewed data, unlimited support on the real line and closed form solutions for fitting their parameters. #SundayMorningPonderings

submitted 19 days ago • 2 comments

As I am looking towards AC meetings in the middle of the night and finalizing paper decisions at least partially during my vacation, I am not as sad anymore to not have been invited to serve as AC for ICCV 😉

submitted 21 days ago • 1 comment

First time I see convincing results of scene coordinate regression for large-scale scenes. Nice!

submitted 23 days ago • 1 comment

In OpenReview, can I e-mail specific reviewers to urge them to join the discussion? It was possible in CMT... I guess I could add a comment, only visible to that specific reviewer. But if they answer that comment, their answer would only be visible to me, I guess? #CVPR2025

submitted 25 days ago • 1 comment

Looks like some authors are mistaking the "confidential comments to AC" field as an opportunity for a second rebuttal. Any criticism of review content belongs in the rebuttal for all to see, and nowhere else. #CVPR2025

submitted 28 days ago • 0 comments

While you are finishing CVPR rebuttal - consider submitting papers to Image Matching Workshop 2025 @cvprconference.bsky.social #CVPR2025 Deadline: March 11, 2025. cmt3.research.microsoft.com/IMW2025

submitted 29 days ago • 0 comments

TPAMI keeps sending me review request of revisions, claiming I was an initial reviewer. But it's not true. Dark pattern to persuade me to agree? 🤔

submitted 30 days ago • 1 comment