From 0440b430f1e93a36e98f3c32c2d398e57019fc72 Mon Sep 17 00:00:00 2001 From: Jianyuan Wang Date: Wed, 19 Mar 2025 22:34:40 +0000 Subject: [PATCH] add single view results from Karim Abou Zeid --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index e302212..0844453 100644 --- a/README.md +++ b/README.md @@ -167,6 +167,10 @@ This plots the tracks on the images and saves them to the specified output direc Our model shows surprisingly good performance on single-view reconstruction, although it was never trained for this task. The model does not need to duplicate the single-view image to a pair, instead, it can directly infer the 3D structure from the tokens of the single view image. Feel free to try it with our demos above, which naturally works for single-view reconstruction. +We did not quantitatively test monocular depth estimation performance ourselves, but @kabouzeid generously provided a comparison of VGGT to recent methods [here](https://github.com/facebookresearch/vggt/issues/36). VGGT shows competitive or better results compared to state-of-the-art monocular approaches such as DepthAnything v2 or MoGe, despite never being explicitly trained for single-view tasks. + + + ## Runtime and GPU Memory We benchmark the runtime and GPU memory usage of VGGT's aggregator on a single NVIDIA H100 GPU across various input sizes.