Eric Brachmann

52 Followers
25 Following
45 Posts

Staff scientist at Niantic.

Throws #MachineLearning at traditional #ComputerVision pipelines to see what sticks. Differentiates the non-differentiable.

Google Scholarhttps://scholar.google.de/citations?user=cAIshsYAAAAJ

Due to requests at #ECCV2022 and to make our #MapFreeReloc dataset useful for more tasks, we make the SfM reconstructions of our train set publicly available.

🔥460 SfM models of outdoor scenes all around the world 🔥
https://research.nianticlabs.com/mapfree-reloc-benchmark/dataset

Want to train 460 NeRFs? Go ahead.

Each scene was captured by non-expert users with two independent scans, sometimes months apart. We reconstructed them with COLMAP and aligned them to the original phone trajectories.

Thus, all models are in metric scale.

Map-free Visual Relocalization - Download

Once, German engineering was renowned throughout the world. But now, 1 is less than min and 9 is more than max.
Happy to report that my innovative engineering genius extends to the playroom. (Any similarities to my papers are coincidental.)