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.

For our mental health, once in a while

we go to the cinema instead of binge watching the latest show,

we listen to that one vinyl instead of streaming a playlist,

we code without copilot,

we write a paper without a LLM.

#SlowScience

To #CVPR2023 reviewers: Remember there are humans on the other end. Be strict in the matter but respectful in tone. Consider even being friendly in tone. Someone worked hard on this, and is proud. Don't bend but sweeten the pill.

Appreciate the strengths even if you recommend rejection. The best way to sweeten the pill is to be constructive. Does your review make clear which concrete improvements would let you accept the draft when resubmitted?