From dcc6f2e8016dd9f9a45082a3e01b373c60404b42 Mon Sep 17 00:00:00 2001 From: xt4d Date: Sun, 9 Jul 2023 14:35:57 +0800 Subject: [PATCH] update --- index.html | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 62 insertions(+), 5 deletions(-) diff --git a/index.html b/index.html index f454200..a34ed34 100644 --- a/index.html +++ b/index.html @@ -7,7 +7,6 @@ ID-Pose -
@@ -67,13 +66,71 @@

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. +

+ +
+
+
+
-

👉 Go to the new Project Page.

-
-
-
+

👉 Open Interactive Demo.

+ + + + +
+
+

BibTeX

+
@article{cheng2023id, 
+   title={ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models}, 
+   author={Cheng, Weihao and Cao, Yan-Pei and Shan, Ying}, 
+   journal={arXiv preprint arXiv:2306.17140}, 
+   year={2023}
+}
+
+
+
+ + \ No newline at end of file