基于NeRF的SLAM正迎来蓬勃的发展: CVPR 2023上,多MLP、对象物体级的vMAP:Vectorised Object Mapping for Neural Field SLAM Arxiv 2023上,引入语义信息的Neural Implicit Dense Semantic SLAM CVPR 2023上,引入TSDF和multi-scale axis-aligned feature planes更有效率的ESLAM:Efficient dense slam system based on hyb...
We propose SNI-SLAM, a semantic SLAM system utilizing neural implicit representation, that simultaneously performs accurate semantic mapping, high-quality surface reconstruction, and robust camera tracking. In this system, we introduce hierarchical semantic representation to allow multi-level semantic compre...
In recent years, the paradigm of neural implicit representations has gained substantial attention in the field of Simultaneous Localization and Mapping (SLAM). However, a notable gap exists in the existing approaches when it comes to scene understanding. In this paper, we introduce NIS-SLAM, an ...
We propose SNI-SLAM, a semantic SLAM system utilizing neural implicit representation, that simultaneously performs accurate semantic mapping, high-quality surface reconstruction, and robust camera tracking. In this system, we introduce hierarchical semantic representation to allow multi-level semantic comprehe...
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM Zihan Zhu1,2∗ Songyou Peng2,4* Viktor Larsson3 Zhaopeng Cui1 † Martin R. Oswald2,5 Weiwei Xu1 Hujun Bao1 Marc Pollefeys2,6 1State Key Lab of CAD&CG, Zhejiang University 2ETH Zurich 3Lund University 4MPI for Intelli...
We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural implicit SLAM systems in high-quality rendering, scene understanding, ...
[CVPR 2023] vMAP: Vectorised Object Mapping for Neural Field SLAM real-timeslamnerf3d-reconstructionobject-mappingvectorizedrgbd-slamneural-fieldsneural-implicit-representationsdense-mappingcvpr2023 UpdatedJun 16, 2023 Python MatrixBrain/awesome-NeRF ...
We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural implicit SLAM systems in high-quality rendering, scene understanding, ...
We present SGS-SLAM, the first semantic visual SLAM system based on 3D Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural implicit SLAM systems in high-quality rendering, scene understanding...
Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In CVPR, 2021. 3 [44] Albert Pumarola, Enric Corona, Gerard Pons-Moll, and Francesc Moreno-Noguer. D-NeRF: Neural Radiance Fields for Dyna...