Skip to content

2020 TPAMI, SurfaceNet+ is a volumetric learning framework for the very sparse MVS. The sparse-MVS benchmark is maintained here. Authors: Mengqi Ji#, Jinzhi Zhang#, Qionghai Dai, Lu Fang.

Notifications You must be signed in to change notification settings

mjiUST/SurfaceNet-plus

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 

Repository files navigation

SurfaceNet+

  • An End-to-end 3D Neural Network for Very Sparse MVS.
  • Key contributions
    1. Proposed a Sparse-MVS benchmark (under construction)
    2. Proposed a trainable occlusion-aware view selection scheme for the volumetric MVS method, e.g., SurfaceNet[5].
    3. Analysed the advantages of the volumetric methods, e.g., SurfaceNet[5] and SurfaceNet+, on the Sparse-MVS problem over the depth-fusion methods, e.g., Gipuma [6], R-MVSNet[7], Point-MVSNet[8], and COLMAP[9].

Fig.1: Illustration of a very sparse MVS setting using only $1/7$ of the camera views, i.e., ${v_i}_{i=1,8,15,22,...}$, to recover the model 23 in the DTU dataset [10]. Compared with the state-of-the-art methods, the proposed SurfaceNet+ provides much complete reconstruction, especially around the boarder region captured by very sparse views.

Fig.2: Comparison with the existing methods in the DTU Dataset [10] with different sparsely sampling strategy. When Sparsity = 3 and Batchsize = 2, the chosen camera indexes are 1,2 / 4,5 / 7,8 / 10,11 / .... SurfaceNet+ constantly outperforms the state-of-the-art methods at all the settings, especially at the very sparse scenario.

Fig.3: Results of a tank model in the Tanks and Temples 'intermediate' set [23] compared with R-MVSNet [7] and COLMAP [9], which demonstrate the power of SurfaceNet+ of high recall prediction in the sparse-MVS setting.

Citing

If you find SurfaceNet+, the Sparse-MVS benchmark, or SurfaceNet useful in your research, please consider citing:

@article{ji2020surfacenet_plus,
    title={SurfaceNet+: An End-to-end 3D Neural Network for Very Sparse Multi-view Stereopsis},
    author={Ji, Mengqi and Zhang, Jinzhi and Dai, Qionghai and Fang, Lu},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year={2020},
    publisher={IEEE}

}

@inproceedings{ji2017surfacenet,
    title={SurfaceNet: An End-To-End 3D Neural Network for Multiview Stereopsis},
    author={Ji, Mengqi and Gall, Juergen and Zheng, Haitian and Liu, Yebin and Fang, Lu},
    booktitle={Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
    pages={2307--2315},
    year={2017}
}

About

2020 TPAMI, SurfaceNet+ is a volumetric learning framework for the very sparse MVS. The sparse-MVS benchmark is maintained here. Authors: Mengqi Ji#, Jinzhi Zhang#, Qionghai Dai, Lu Fang.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published