건축 컴퓨터 비전/Computer Vision

다양한 visual slam 자료

시도하고 시도 2022. 7. 8. 22:48

https://github.com/tum-vision/LDSO

 

GitHub - tum-vision/LDSO: DSO with SIM(3) pose graph optimization and loop closure

DSO with SIM(3) pose graph optimization and loop closure - GitHub - tum-vision/LDSO: DSO with SIM(3) pose graph optimization and loop closure

github.com

 

https://github.com/tum-vision/online_photometric_calibration

 

GitHub - tum-vision/online_photometric_calibration: Implementation of online photometric calibration (https://vision.in.tum.de/r

Implementation of online photometric calibration (https://vision.in.tum.de/research/vslam/photometric-calibration) - GitHub - tum-vision/online_photometric_calibration: Implementation of online pho...

github.com

 

https://github.com/lukasvst/dm-vio

 

GitHub - lukasvst/dm-vio: Source code for the paper DM-VIO: Delayed Marginalization Visual-Inertial Odometry

Source code for the paper DM-VIO: Delayed Marginalization Visual-Inertial Odometry - GitHub - lukasvst/dm-vio: Source code for the paper DM-VIO: Delayed Marginalization Visual-Inertial Odometry

github.com

 

dso에는 카메라 캘리브레이션에 대한 친절한 안내사항도 있다고 한다.

https://github.com/JakobEngel/dso

 

GitHub - JakobEngel/dso: Direct Sparse Odometry

Direct Sparse Odometry. Contribute to JakobEngel/dso development by creating an account on GitHub.

github.com

 

 

https://www.vincentsitzmann.com/metasdf/

 

MetaSDF: Meta-learning Signed Distance Functions

Reconstructing SDFs from Dense Samples We can recover an SDF by supervising with dense, ground-truth samples from the signed distance function, as proposed in DeepSDF, or with a point cloud taken from the zero-level set (mesh surface), similar to a PointNe

www.vincentsitzmann.com

 

추가로 3d reconstruction 패키지 siren에 관한 정보다

https://www.vincentsitzmann.com/siren/

 

Implicit Neural Representations with Periodic Activation Functions

Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations. However, current network architectures for such i

www.vincentsitzmann.com

 

 

3d semantic segmentation

https://www.computationalimaging.org/publications/semantic-srn/