Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

🤖 Plain-English Summary

We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. Finally, evaluation on five inward-facing benchmarks shows that our method matches, if not surpasses, NeRF's quality, yet it only takes about 15 minutes to train from scratch for a new scene.

🔑 Key Findings

• This task, which is often applied to novel view synthesis, is recently revolution-ized by Neural Radiance Field (NeRF) for its advanced quality and fiexibility.
• However, NeRF and its variants require a lengthy training time ranging from hours to days for a single scene.
• In contrast, our approach achieves NeRF-comparable quality and converges rapidly from scratch in less than 15 minutes with a single GPU.

🔗 Related Resources