Journal
IEEE ROBOTICS AND AUTOMATION LETTERS
Volume 8, Issue 11, Pages 7138-7145Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2023.3311365
Keywords
Dense SLAM; neural implicit coding; surface rendering
Categories
Ask authors/readers for more resources
In this paper, we propose an end-to-end 3D reconstruction system that achieves fine scene reconstruction without prior information by utilizing a neural implicit encoding. Our approach, with improved decoders and a keyframe selection strategy, can compete with widely adopted NeRF-based SLAM methods in terms of 3D reconstruction accuracy.
An accurate and generalizable dense 3D reconstruction system has attracted much attention. However, existing 3D dense reconstruction systems are constrained by pre-training, and there is a need for enhanced reconstruction of texture and shape details. We propose an end-to-end 3D reconstruction system which achieves fine scene reconstruction without prior information by utilizing a neural implicit encoding. Our proposed system successfully achieves the goal through improved multi-MLP decoders (MLM) and an effective keyframe selection strategy. Experiments conducted on the commonly used Replica and TUM RGB-D datasets demonstrate that our approach can compete with widely adopted NeRF-based SLAM methods in terms of 3D reconstruction accuracy. Moreover, our approach shows a 40.8%(except Completion Ratio) improvement in accuracy compared to NICE-SLAM [14] and does not use prior information.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available