From da7b488e4f334394bca4c69511ec8ad53a0e5723 Mon Sep 17 00:00:00 2001 From: kwea123 Date: Fri, 1 May 2020 23:51:20 +0900 Subject: [PATCH] add --- README.md | 6 +++++- README_mesh.md | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) create mode 100644 README_mesh.md diff --git a/README.md b/README.md index 177eb3bd..f8b59b6a 100644 --- a/README.md +++ b/README.md @@ -9,7 +9,7 @@ Reference pytorch implementation: [nerf-pytorch](https://github.com/yenchenlin/n * Multi-gpu training: Training on 8 GPUs finishes within 1 hour for the synthetic dataset! * [Colab](#colab) notebooks to allow easy usage! -* Reconstruct **colored** mesh! +* [Reconstruct](#mesh) **colored** mesh! # Installation @@ -139,6 +139,10 @@ Example of own scene ([Silica GGO figure](https://www.youtube.com/watch?v=hVQIvE

+# Mesh + +See [README_mesh](README_mesh.md) for reconstruction of **colored** mesh. Only supported for blender dataset and 360 inward-facing data! + # Notes on differences with the original repo * The learning rate decay in the original repo is **by step**, which means it decreases every step, here I use learning rate decay **by epoch**, which means it changes only at the end of 1 epoch. diff --git a/README_mesh.md b/README_mesh.md new file mode 100644 index 00000000..e36cb74b --- /dev/null +++ b/README_mesh.md @@ -0,0 +1 @@ +# Reconstruct mesh \ No newline at end of file