Loading video...
Video Failed to Load
(1/2) Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation #ECCV2024! We show a theoretical derivation to create radiance fields directly from meshes. Thus, we can obtain GT training data for generative NeRF methods.
16,835 views • 1 year ago •via X (Twitter)
2 Comments

Matthias Niessner1 year ago
(2/2) Main idea: Mesh2NeRF characterizes the density field as an occupancy function around the surface, and it determines view-dependent color through its underlying reflection function. Great work by @YujinChen_cv, @yinyu_nie, B. Ummenhofer, R. Birkl, M. Paulitsch, M. Mueller.

Eugene1 year ago
That’s a huge improvement! ✨
