no code implementations • 22 Apr 2024 • Yinzhe Xu, Huajian Huang, Yingshu Chen, Sai-Kit Yeung
Visual object tracking and segmentation in omnidirectional videos are challenging due to the wide field-of-view and large spherical distortion brought by 360{\deg} images.
no code implementations • 16 Apr 2024 • Yingshu Chen, Huajian Huang, Tuan-Anh Vu, Ka Chun Shum, Sai-Kit Yeung
We then optimize the scene style globally by adapting the scale of the style image with the scale of the training views.
no code implementations • 4 Apr 2024 • Longwei Li, Huajian Huang, Sai-Kit Yeung, Hui Cheng
In this paper, we present OmniGS, a novel omnidirectional Gaussian splatting system, to take advantage of omnidirectional images for fast radiance field reconstruction.
no code implementations • 27 Mar 2024 • Changkun Liu, Huajian Huang, Zhengyang Ma, Tristan Braud
State-of-the-art (SOTA) hierarchical localisation pipelines (HLoc) rely on image retrieval (IR) techniques to establish 2D-3D correspondences by selecting the $k$ most similar images from a reference image database for a given query image.
1 code implementation • 22 Feb 2024 • Changkun Liu, Shuai Chen, Yukun Zhao, Huajian Huang, Victor Prisacariu, Tristan Braud
In addition, we take advantage of the uncertainty for pose refinement to enhance the performance of APR.
no code implementations • 29 Nov 2023 • Huajian Huang, Changkun Liu, Yipeng Zhu, Hui Cheng, Tristan Braud, Sai-Kit Yeung
We propose a virtual camera approach to generate lower-FoV query frames from 360$^\circ$ images, which ensures a fair comparison of performance among different query types in visual localization tasks.
1 code implementation • 28 Nov 2023 • Huajian Huang, Longwei Li, Hui Cheng, Sai-Kit Yeung
In addition to actively densifying hyper primitives based on geometric features, we further introduce a Gaussian-Pyramid-based training method to progressively learn multi-level features, enhancing photorealistic mapping performance.
1 code implementation • ICCV 2023 • Huajian Huang, Yinzhe Xu, Yingshu Chen, Sai-Kit Yeung
360{\deg} images can provide an omnidirectional field of view which is important for stable and long-term scene perception.
no code implementations • 4 Aug 2022 • Huajian Huang, Yingshu Chen, Tianjia Zhang, Sai-Kit Yeung
Subsequently, we assign local radiance fields through an adaptive divide-and-conquer strategy based on the recovered geometry.
no code implementations • 23 Sep 2020 • Huajian Huang, Wen-Yan Lin, Siying Liu, Dong Zhang, Sai-Kit Yeung
As local pose estimation is ill-conditioned, local pose estimation failures happen regularly, making the overall SLAM system brittle.