From e3d42d48846a64114d2c200821b51bd955226554 Mon Sep 17 00:00:00 2001 From: Stefan Baumann Date: Sun, 27 Aug 2023 16:22:02 +0200 Subject: [PATCH] Corrected inequalities in documentation of visibility rendering methods The documentation of these methods stated "greater-than" inequalities while the code performed "greater-than-or-equal-to" --- nerfacc/volrend.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/nerfacc/volrend.py b/nerfacc/volrend.py index 62907a28..8fdee1e8 100644 --- a/nerfacc/volrend.py +++ b/nerfacc/volrend.py @@ -377,7 +377,7 @@ def render_visibility_from_alpha( In this function, we first compute the transmittance from the sample opacity. The transmittance is then used to filter out occluded samples. And opacity is used to filter out transparent samples. The function returns a boolean tensor indicating - which samples are visible (`transmittance > early_stop_eps` and `opacity > alpha_thre`). + which samples are visible (`transmittance >= early_stop_eps` and `opacity >= alpha_thre`). This function supports both batched and flattened input tensor. For flattened input tensor, either (`packed_info`) or (`ray_indices` and `n_rays`) should be provided. @@ -435,7 +435,7 @@ def render_visibility_from_density( In this function, we first compute the transmittance and opacity from the sample density. The transmittance is then used to filter out occluded samples. And opacity is used to filter out transparent samples. The function returns a boolean tensor indicating - which samples are visible (`transmittance > early_stop_eps` and `opacity > alpha_thre`). + which samples are visible (`transmittance >= early_stop_eps` and `opacity >= alpha_thre`). This function supports both batched and flattened input tensor. For flattened input tensor, either (`packed_info`) or (`ray_indices` and `n_rays`) should be provided.