MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstruction

no code implementations • 6 Feb 2024 • Heng Zhou, Zhetao Guo, Shuhong Liu, Lechen Zhang, Qihao Wang, Yuxiang Ren, Mingrui Li

Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints.

3D Reconstruction 3D Scene Reconstruction +4

SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM

no code implementations • 5 Feb 2024 • Mingrui Li, Shuhong Liu, Heng Zhou, Guohao Zhu, Na Cheng, Tianchen Deng, Hongyu Wang

We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting.

3D Semantic Segmentation Object +4

DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM

no code implementations • 3 Jan 2024 • Mingrui Li, Yiming Zhou, Guangan Jiang, Tianchen Deng, Yangyang Wang, Hongyu Wang

To address dynamic tracking interferences, we propose a feature point segmentation method that combines semantic features with a mixed Gaussian distribution model.

Loop Closure Detection Optical Flow Estimation +1

ID2image: Leakage of non-ID information into face descriptors and inversion from descriptors to images

no code implementations • 15 Apr 2023 • Mingrui Li, William A. P. Smith, Patrik Huber

Information about the environment (such as background and lighting) or changeable aspects of the face (such as pose, expression, presence of glasses, hat etc.)

Face Recognition