From 3df47d6394f81ca6159e7957d92f6fdb0939e8e8 Mon Sep 17 00:00:00 2001 From: xt4d Date: Tue, 2 Jan 2024 01:29:02 +0800 Subject: [PATCH] redirect --- index.html | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/index.html b/index.html index ad9563d..1151c9a 100644 --- a/index.html +++ b/index.html @@ -1,4 +1,7 @@ + @@ -88,16 +91,7 @@
I

Abstract

- Given sparse views of an object, estimating their camera poses is a long-standing and intractable - problem. We harness the pre-trained diffusion model of novel views conditioned on viewpoints - (Zero-1-to-3). We present ID-Pose which inverses the denoising diffusion process to estimate the - relative pose given two input images. ID-Pose adds a noise on one image, and predicts the noise - conditioned on the other image and a decision variable for the pose. The prediction error is used as - the objective to find the optimal pose with the gradient descent method. ID-Pose can handle more - than two images and estimate each of the poses with multiple image pairs from triangular - relationships. ID-Pose requires no training and generalizes to real-world images. We conduct - experiments using high-quality real-scanned 3D objects, where ID-Pose significantly outperforms - state-of-the-art methods. + Given sparse views of a 3D object, estimating their camera poses is a long-standing and intractable problem. Toward this goal, we consider harnessing the pre-trained diffusion model of novel views conditioned on viewpoints (Zero-1-to-3). We present ID-Pose which inverses the denoising diffusion process to estimate the relative pose given two input images. ID-Pose adds a noise to one image, and predicts the noise conditioned on the other image and a hypothesis of the relative pose. The prediction error is used as the minimization objective to find the optimal pose with the gradient descent method. We extend ID-Pose to handle more than two images and estimate each pose with multiple image pairs from triangular relations. ID-Pose requires no training and generalizes to open-world images. We conduct extensive experiments using casually captured photos and rendered images with random viewpoints. The results demonstrate that ID-Pose significantly outperforms state-of-the-art methods.
