1 code implementation • 20 Mar 2024 • Chen Zhao, Tong Zhang, Zheng Dang, Mathieu Salzmann
Determining the relative pose of an object between two images is pivotal to the success of generalizable object pose estimation.
no code implementations • 5 Dec 2023 • Zhi Chen, Yufan Ren, Tong Zhang, Zheng Dang, Wenbing Tao, Sabine Süsstrunk, Mathieu Salzmann
We propose formulating PCR as a denoising diffusion probabilistic process, mapping noisy transformations to the ground truth.
no code implementations • ICCV 2023 • Zheng Dang, Mathieu Salzmann
Specifically, AutoSynth automatically curates an optimal dataset by exploring a search space encompassing millions of potential datasets with diverse 3D shapes at a low cost. To achieve this, we generate synthetic 3D datasets by assembling shape primitives, and develop a meta-learning strategy to search for the best training data for 3D registration on real point clouds.
1 code implementation • CVPR 2023 • Haobo Jiang, Zheng Dang, Zhen Wei, Jin Xie, Jian Yang, Mathieu Salzmann
Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.
no code implementations • ICCV 2023 • Haobo Jiang, Zheng Dang, Shuo Gu, Jin Xie, Mathieu Salzmann, Jian Yang
Our method decouples the translation from the entire transformation by predicting the object center and estimating the rotation in a center-aware manner.
no code implementations • 29 Mar 2022 • Zheng Dang, Lizhou Wang, Yu Guo, Mathieu Salzmann
Our two contributions are general and can be applied to many existing learning-based 3D object registration frameworks, which we illustrate by implementing them in two of them, DCP and IDAM.
no code implementations • 19 Nov 2021 • Zheng Dang, Lizhou Wang, Junning Qiu, Minglei Lu, Mathieu Salzmann
We summarise our findings into a set of guidelines and demonstrate their effectiveness by applying them to different baseline methods, DCP and IDAM.
2 code implementations • 8 Apr 2021 • Wei Wang, Zheng Dang, Yinlin Hu, Pascal Fua, Mathieu Salzmann
Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms.
no code implementations • 23 Nov 2020 • Zheng Dang, Fei Wang, Mathieu Salzmann
While much progress has been made on the task of 3D point cloud registration, there still exists no learning-based method able to estimate the 6D pose of an object observed by a 2. 5D sensor in a scene.
no code implementations • 17 Nov 2020 • Minglei Lu, Yu Guo, Fei Wang, Zheng Dang
Recently, 3D version has been improved greatly due to the development of deep neural networks.
no code implementations • 8 Jun 2020 • Zheng Dang, Fei Wang, Mathieu Salzmann
While 3D-3D registration is traditionally tacked by optimization-based methods, recent work has shown that learning-based techniques could achieve faster and more robust results.
no code implementations • 15 Apr 2020 • Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann
In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network.
2 code implementations • NeurIPS 2019 • Wei Wang, Zheng Dang, Yinlin Hu, Pascal Fua, Mathieu Salzmann
Eigendecomposition (ED) is widely used in deep networks.
no code implementations • ECCV 2018 • Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system.