Hacker News Reader

Thanks for your work!

From my experience, NERF works great, but depends on highly accurate camera location information. Unless the VR device has this baked in, one must run a Colmap-style or SFM-style process to generate those camera extrinsics. Is there anything special HybridNeRF does around this?

View on HN

The method in this paper relies on precomputed camera poses as input, but there have been tons of papers published on the topic of eliminating this requirement. Here are a few: https://dust3r.europe.naverlabs.com/ https://arxiv.org/abs/2102.07064 https://arxiv.org/abs/2312.08760v1 https://x.com/_akhaliq/status/1734803566802407901

Your understanding is correct!

Reply on news.ycombinator.com