Eric Brachmann
@ericbrachmann.bsky.social
2K followers 540 following 350 posts
Niantic Spatial, Research. Throws machine learning at traditional computer vision pipelines to see what sticks. Differentiates the non-differentiable. 📍Europe 🔗 http://ebrach.github.io
Posts Media Videos Starter Packs
Pinned
ericbrachmann.bsky.social
⏩ FastForward ⏩ A new model for efficient visual relocalization. Accurate camera poses without building structured 3D maps.

nianticspatial.github.io/fastforward/

Work by @axelbarroso.bsky.social, Tommaso Cavallari and Victor Adrian Prisacariu.
ericbrachmann.bsky.social
Just from todays feed: bsky.app/profile/kmyi...
kmyid.bsky.social
Yugay and Nguyen et al., “Visual Odometry with Transformers”

Instead of point maps, you can also directly output poses. This used to be much less accurate, but now it's the opposite. Simple architecture that directly predicts camera embeddings, which then regress rot and trans.
ericbrachmann.bsky.social
I think it is a great time to have such a tutorial again. As we see competitive RANSAC-free approaches arise, it is worth looking back - and looking forward.
ducha-aiki.bsky.social
For those going to @iccv.bsky.social, welcome to our RANSAC tutorial on October 2025 with
- Daniel Barath
- @ericbrachmann.bsky.social
- Viktor Larsson
- Jiri Matas
- and me
danini.github.io/ransac-2025-...
#ICCV2025
Reposted by Eric Brachmann
ducha-aiki.bsky.social
For those going to @iccv.bsky.social, welcome to our RANSAC tutorial on October 2025 with
- Daniel Barath
- @ericbrachmann.bsky.social
- Viktor Larsson
- Jiri Matas
- and me
danini.github.io/ransac-2025-...
#ICCV2025
ericbrachmann.bsky.social
Whenever I do a voice over, I realize that I sound like Arnold Schwarzenegger when I say "coordinate". Unfortunately, in my line of work, I have to say "coordinate" a lot...
ericbrachmann.bsky.social
I thought you just turned 34?
ericbrachmann.bsky.social
Trendy.
si-cv-graphics.bsky.social
𝗔 𝗦𝗰𝗲𝗻𝗲 𝗶𝘀 𝗪𝗼𝗿𝘁𝗵 𝗮 𝗧𝗵𝗼𝘂𝘀𝗮𝗻𝗱 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀: 𝗙𝗲𝗲𝗱-𝗙𝗼𝗿𝘄𝗮𝗿𝗱 𝗖𝗮𝗺𝗲𝗿𝗮 𝗟𝗼𝗰𝗮𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗮 𝗖𝗼𝗹𝗹𝗲𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝗜𝗺𝗮𝗴𝗲 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀
Axel Barroso-Laguna, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann
arxiv.org/abs/2510.00978
Trending on www.scholar-inbox.com
ericbrachmann.bsky.social
Great to have Kwang on Bluesky! (And quite flattering that this is his first post 😳)
kmyid.bsky.social
Barroso-Laguna et al., "A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features"

When contexting your feed-forward 3D point-map estimator, don't use full image pairs -- just randomly subsample! -> fast compute, more images.
ericbrachmann.bsky.social
The model estimates image poses relative to images of which you already know the poses. It solves a sub-problem of what COLMAP generally is used for. FastForward is a visual relocalization model, not a full structure-from-motion model.
ericbrachmann.bsky.social
*whisper* Only one way to know...
Reposted by Eric Brachmann
ericzzj.bsky.social
A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features

@axelbarroso.bsky.social, Tommaso Cavallari, Victor Adrian Prisacariu, @ericbrachmann.bsky.social

arxiv.org/abs/2510.00978
ericbrachmann.bsky.social
FastForward was trained on challenging frame sets. Therefore, it is able to solve difficult relocalization cases, like opposing shots in the video below. We only have mapping images of the front of the sign. Still FF relocalizes well even behind the sign.
ericbrachmann.bsky.social
FastForward uses 20 retrieved images by default. But no need to compute attention over 21 images. To keep the model lean, we sub-sample the feature tokens of mapping images.

Each token is combined with its ray embedding. Hence, FastForward operates on samples of visual tokens in scene space.
ericbrachmann.bsky.social
Building visual maps via reconstruction (SfM, SCR) can take time. Instead:

⏩ Get poses for your mapping images, e.g. via SLAM in real time.
⏩ Build a retrieval index in seconds.
⏩ FastForward predicts the relative pose between a query image and all retrieved images in one forward pass.
ericbrachmann.bsky.social
⏩ FastForward ⏩ A new model for efficient visual relocalization. Accurate camera poses without building structured 3D maps.

nianticspatial.github.io/fastforward/

Work by @axelbarroso.bsky.social, Tommaso Cavallari and Victor Adrian Prisacariu.
ericbrachmann.bsky.social
I agree, could have been the sächsische Schweiz easily from the image.
ericbrachmann.bsky.social
"jokes and nonsense"

Add awkward motivational spins and you have LinkedIn.
ericbrachmann.bsky.social
Limitations of pseudo ground truth.
ericbrachmann.bsky.social
Our software engineering prof pretty much told us exactly that. And that you will earn a lot of money if you master that skill.
ericbrachmann.bsky.social
Small but important quality of life update by @rerun.io: Customizable frustum colors. Finally we can distinguish estimates and ground truth in the same 3D view ;)
Reposted by Eric Brachmann
csprofkgd.bsky.social
Here we go again 😅 This time I’m planning to take a more senior role to help mentor the next gen of publicity chairs. Please consider volunteering!
cvprconference.bsky.social
#CVPR2026 is looking for Publicity Chairs! The role includes working as part of a team to share conference updates across social media (X, Bluesky, etc.) and answering community questions.

Interested? Check out the self-nomination form in the thread.
ericbrachmann.bsky.social
Recovering 6D Object Pose - Looking forward to the R6D workshop at #ICCV2025 in Hawaii! (not looking forward to the jet lag)

cmp.felk.cvut.cz/sixd/worksho...

The accompanying challenge is still open for submissions until Oct 1st. And the workshop also still accepts non-proceeding paper submission!
ericbrachmann.bsky.social
Maybe it deals better with a French accent than with a Saxon accent 🫣