1 code implementation • 15 Jul 2024 • Yuzhou Liu, Lingjie Zhu, Xiaodong Ma, Hanqiao Ye, Xiang Gao, Xianwei Zheng, Shuhan Shen
To tackle these challenges, we present PolyRoom, a room-aware Transformer that leverages uniform sampling representation, room-aware query initialization, and room-aware self-attention for floorplan reconstruction.
1 code implementation • 11 Mar 2024 • Fudong Ge, Yiwei Zhang, Shuhan Shen, Yue Wang, Weiming Hu, Jin Gao
2) The lower layers of the pre-trained backbone from BEV generation are shared for visual and structural streams in VPR, facilitating the learning of fine-grained local features in the visual stream.
1 code implementation • CVPR 2024 • Yujie Lu, Long Wan, Nayu Ding, Yulong Wang, Shuhan Shen, Shen Cai, Lin Gao
However, common distance field based implicit representations, specifically signed distance field (SDF) for watertight shapes or unsigned distance field (UDF) for arbitrary shapes, routinely suffer from degradation of reconstruction accuracy when converting to explicit surface points and meshes.
1 code implementation • 28 Feb 2024 • Shen Cai, Zhanhao Wu, Lingxi Guo, Jiachun Wang, Siyu Zhang, Junchi Yan, Shuhan Shen
Under the minimal $4$-point configuration, the first and the last similarity transformations in SKS are computed by two anchor points on target and source planes, respectively.
no code implementations • CVPR 2024 • Peilin Tao, Hainan Cui, Mengqi Rong, Shuhan Shen
Then we highlight the superiority of the objective function based on the cross-product distance metric and propose a novel explicit global translation estimation framework that integrates both relative translations and feature tracks as input.
no code implementations • CVPR 2024 • Diantao Tu, Hainan Cui, Xianwei Zheng, Shuhan Shen
Instead of solving the problem in the motion averaging phase we focus on estimating scaled relative pose with the help of panoramic cameras and deep neural networks.
no code implementations • 29 Sep 2023 • Xiang Gao, Hainan Cui, Shuhan Shen
In addition, to further address the limitations of the existing rotation averaging benchmark of relying on the slightly outdated Bundler camera calibration results as ground truths and focusing solely on rotation estimation accuracy, this paper presents a new COLMAP-based rotation averaging benchmark that incorporates a cross check between COLMAP and Bundler, and employ the accuracy of both rotation and downstream location estimation as evaluation metrics, which is desired to provide a more reliable and comprehensive evaluation tool for the rotation averaging research.
1 code implementation • ICCV 2023 • Mingyue Dong, Linxi Huan, Hanjiang Xiong, Shuhan Shen, Xianwei Zheng
This paper proposes a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene understanding.
no code implementations • 21 May 2020 • Tianxin Shi, Hainan Cui, Zhuo Song, Shuhan Shen
Visual localization plays an important role in many applications.
1 code implementation • 23 Dec 2019 • Yu Chen, Shuhan Shen, Yisong Chen, Guoping Wang
After local reconstructions, we construct a minimum spanning tree (MinST) to find accurate similarity transformations.
no code implementations • 21 Apr 2019 • Xiang Gao, Shuhan Shen, Lingjie Zhu, Tianxin Shi, Zhiheng Wang, Zhanyi Hu
Experimental evaluations on two ancient Chinese architecture datasets demonstrate the effectiveness of our proposed complete scene reconstruction pipeline.
no code implementations • 8 Apr 2019 • Tianxin Shi, Shuhan Shen, Xiang Gao, Lingjie Zhu
Accurate and robust visual localization under a wide range of viewing condition variations including season and illumination changes, as well as weather and day-night variations, is the key component for many computer vision and robotics applications.
no code implementations • ECCV 2018 • Lingjie Zhu, Shuhan Shen, Xiang Gao, Zhanyi Hu
There are two major steps in our framework: segmentation and building modeling.
no code implementations • 23 Mar 2018 • Hainan Cui, Shuhan Shen, Xiang Gao, Zhanyi Hu
The global manner has the advantage of simultaneously estimating all camera poses, but it is usually sensitive to epipolar geometry outliers.
no code implementations • CVPR 2017 • Hainan Cui, Xiang Gao, Shuhan Shen, Zhanyi Hu
In this work, we propose a new hybrid SfM method to tackle the issues of efficiency, accuracy and robustness in a unified framework.
no code implementations • 1 Dec 2015 • Miao Yu, Shuhan Shen, Zhanyi Hu
Through both the splitting and merging, we further propose a dynamic parallel and distributed graph-cuts algorithm with guaranteed convergence to the globally optimal solutions within a predefined number of iterations.