no code implementations • 1 Feb 2024 • Jiayang Bai, Letian Huang, Jie Guo, Wen Gong, Yuanqi Li, Yanwen Guo
This technique typically takes perspective images as input and optimizes a set of 3D elliptical Gaussians by splatting them onto the image planes, resulting in 2D Gaussians.
no code implementations • 1 Feb 2024 • Letian Huang, Jiayang Bai, Jie Guo, Yuanqi Li, Yanwen Guo
This paper addresses the projection error function of 3D Gaussian Splatting, commencing with the residual error from the first-order Taylor expansion of the projection function.
no code implementations • 18 Mar 2023 • Jiayang Bai, Zhen He, Shan Yang, Jie Guo, Zhenyu Chen, Yan Zhang, Yanwen Guo
Recent methods mostly rely on convolutional neural networks (CNNs) to fill the missing contents in the warped panorama.
no code implementations • 10 Mar 2023 • Jiayang Bai, Letian Huang, Wen Gong, Jie Guo, Yanwen Guo
Recently, Neural Radiance Fields (NeRF) have emerged as a potent method for synthesizing novel views from a dense set of images.
no code implementations • 13 Feb 2022 • Jiayang Bai, Jie Guo, Chenchen Wan, Zhenyu Chen, Zhen He, Shan Yang, Piaopiao Yu, Yan Zhang, Yanwen Guo
At its core is a new lighting model (dubbed DSGLight) based on depth-augmented Spherical Gaussians (SG) and a Graph Convolutional Network (GCN) that infers the new lighting representation from a single LDR image of limited field-of-view.
1 code implementation • 6 Feb 2022 • Jiayang Bai, Shuichang Lai, Haoyu Qin, Jie Guo, Yanwen Guo
In this paper, we propose a learning-based method for predicting dense depth values of a scene from a monocular omnidirectional image.
Ranked #7 on Depth Estimation on Stanford2D3D Panoramic