From 86d6f883b2da4b7ed984e54d04c6643b10d0f3b1 Mon Sep 17 00:00:00 2001 From: Kai Zhang Date: Fri, 16 Oct 2020 00:24:18 -0400 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 58cb942..e907213 100644 --- a/README.md +++ b/README.md @@ -15,7 +15,7 @@ Codebase for arXiv preprint ["NeRF++: Analyzing and Improving Neural Radiance Fi * Intrinsics and poses are stored as flattened 4x4 matrices (row-major). * Pixel coordinate of an image's upper-left corner is (column, row)=(0, 0), lower-right corner is (width-1, height-1). * Poses are camera-to-world, not world-to-camera transformations. - * Opencv camera coordinate system is adopted, i.e., x--->right, y--->down, z--->scene. + * Opencv camera coordinate system is adopted, i.e., x--->right, y--->down, z--->scene. Similarly, intrinsic matrix also follows Opencv convention. * To convert camera poses between Opencv and Opengl conventions, the following code snippet can be used for both Opengl2Opencv and Opencv2Opengl. ```python import numpy as np