flâneur — a map of the web's best reading

NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video

zju3dv.github.io · 690 words · saved by 1 readers

NeuralRecon reconstructs 3D scene geometry from a monocular video with known camera poses in real-time. Accepted in CVPR 2021 as oral.

Explore this link on the map →

saved by