Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction

By Silvano Galliani, Konrad Schindler. 2016

25 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

1. Zexiang Xu
2. Hao Su
3. Konrad Schindler
4. Juergen Gall
5. Lu Fang
6. Yebin Liu
7. Luc Van Gool
8. Ravi Ramamoorthi

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jitendra Malik
3. Juergen Gall
4. Xiaogang Wang
5. Ming-Hsuan Yang
6. Dacheng Tao
7. Andreas Geiger
8. Andrea Vedaldi

Citations in the corpus

• SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis (2017, methodology): “In [10], a CNN is trained to predict the normals of a given depth map based on image appearance.”
• Deep Depth Completion of a Single RGB-D Image (2018, unknown): “[19] used surface normals to recover missing geometry in multi-view reconstruction for table-top objects.”
• Learned Multi-patch Similarity (2017, background): “We note that there is also a large body of work termed “multi-view reconstruction” that in fact computes depth maps from two views and focuses on integrating the corresponding 3D point clouds into implicit [7, 25] or explicit [5] surface representations.”
• Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness (2019, background): “Some of them leverage normal information as well [14, 15].”