NeRF++: Analyzing and Improving Neural Radiance Fields | Free View Synthesis | Vladlen Koltun

NeRF++: Analyzing and Improving Neural Radiance Fields | Free View Synthesis | Vladlen Koltun

Oct 16, 2020
|
107 views
|
Details
Keynote for the DAGM GCPR / VMV / VCBM joint conference on September 28, 2020, that discusses Free View Synthesis (FVS) paper and NeRF++ paper. Neural Radiance Fields (NeRF) achieve impressive view synthesis results for a variety of capture settings, including 360 capture of bounded scenes and forward-facing capture of bounded and unbounded scenes. NeRF fits multi-layer perceptrons (MLPs) representing view-invariant opacity and view-dependent color volumes to a set of training images, and samples novel views based on volume rendering techniques. In this technical report, we first remark on radiance fields and their potential ambiguities, namely the shape-radiance ambiguity, and analyze NeRF's success in avoiding such ambiguities. Second, we address a parametrization issue involved in applying NeRF to 360 captures of objects within large-scale, unbounded 3D scenes. Our method improves view synthesis fidelity in this challenging scenario.

00:52 Outline 2:20 Introduction 14:28 Free View Synthesis 33:10 NeRF++: Analyzing and Improving Neural Radiance Fields
Comments
loading...