Stay Positive: Non-Negative Image Synthesis for Augmented Reality

Luo, Katie; Yang, Guandao; Xian, Wenqi; Haraldsson, Harald; Hariharan, Bharath; Belongie, Serge

doi:10.1109/cvpr46437.2021.00992

Cited by 4 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a key technology in computer vision, 3D representation can directly reflect 3D scenes by adding depth information compared with traditional 2D representation. It is widely used in 3D scene restoration, Simultaneous Localization And Mapping (SLAM) [33,34], Augmented Reality (AR) [35] and other fields. Common 3D expressions can be divided into explicit and implicit:…”

Section: Common Three-dimensional Expressionmentioning

confidence: 99%

Overview of image-based 3D reconstruction technology

Niu,

Liu,

Huang

et al. 2024

J. Eur. Opt. Society-Rapid Publ.

View full text Add to dashboard Cite

Three-dimensional(3D) reconstruction technology is the key technology to establish and express the objective world by using computer, and it is widely used in real 3D, automatic driving, aerospace, navigation and industrial robot applications. According to different principles, it is mainly divided into methods based on traditional multi-view geometry and methods based on deep learning. This paper introduces the above methods from the perspective of three-dimensional space representation. The feature extraction and stereo matching theory of traditional 3D reconstruction methods are the theoretical basis of 3D reconstruction methods based on deep learning, so the paper focuses on them. With the development of traditional 3D reconstruction methods and the development of deep learning related theories, the explicit deep learning 3D reconstruction method represented by MVSNet and the implicit 3D reconstruction method represented by NeRF have been gradually developed. At the same time, the dataset and evaluation indicators for 3D reconstruction were introduced. Finally, a summary of image based 3D reconstruction was provided. Deep networks based on deep learning have been widely used in computer vision, especially the application of deep learning in depth networks of depth estimation, which will eventually realize real-time pixel-level reconstruction of 3D scenes at different scales.

show abstract

Section: Common Three-dimensional Expressionmentioning

confidence: 99%

Overview of image-based 3D reconstruction technology

Niu,

Liu,

Huang

et al. 2024

J. Eur. Opt. Society-Rapid Publ.

View full text Add to dashboard Cite

show abstract

“…Three-dimensional reconstruction provides digital 3D models by presenting a realworld scene, promoting the development of augmented reality, such as autonomous driving and digital twins [1][2][3][4][5]. On the other hand, point cloud data is fundamental for building a digital 3D model because 3D point cloud registration is the core technology for achieving 3D reconstruction by providing stereoscopic models [6,7]. In recent years, the rapid development of sensor technologies enables 3D point cloud data to visualize the world, further promoting technology innovation in practice.…”

Section: Introductionmentioning

confidence: 99%

GraM: Geometric Structure Embedding into Attention Mechanisms for 3D Point Cloud Registration

Liu,

Zhong,

Wang

et al. 2024

Electronics

View full text Add to dashboard Cite

3D point cloud registration is a crucial technology for 3D scene reconstruction and has been successfully applied in various domains, such as smart healthcare and intelligent transportation. With theoretical analysis, we find that geometric structural relationships are essential for 3D point cloud registration. The 3D point cloud registration method achieves excellent performance only when fusing local and global features with geometric structure information. Based on these discoveries, we propose a 3D point cloud registration method based on geometric structure embedding into the attention mechanism (GraM), which can extract the local features of the non-critical point and global features of the corresponding point containing geometric structure information. According to the local and global features, the simple regression operation can obtain the transformation matrix of point cloud pairs, thereby eliminating the semantics that ignores the geometric structure relationship. GraM surpasses the state-of-the-art results by 0.548° and 0.915° regarding the relative rotation error on ModelNet40 and LowModelNet40, respectively.

show abstract