Our paper on voxelized renderable neural 3D spatial representation is accepted to IEEE RA-L
[2025.10.20]
The following paper is accepted to the IEEE Robotics and Automation Letters (RA-L):
Memory-Efficient Voxelized Renderable Neural 3D Spatial Representation for Vision-Based Robotics by Howoong Jun, Seongbo Ha, Jaewon Lee, Hyeonwoo Yu, and Songhwai Oh
- Abstract: In this paper, we introduce a novel approach for modeling a memory-efficient spatial representation with 3D Gaussian splatting. Efficient vision-based spatial representation poses a significant challenge due to the memory demands of visual information. Recent advances in 3D rendering technologies, such as neural radiance fields (NeRF) and 3D Gaussian splatting, have prompted exploration of their applications in robotics. However, such 3D rendering methods often focus on rendering high-quality images, requiring numerous parameters and resulting in large data, which are unsuitable for robotics applications. To tackle this challenge, we introduce 3DSR, an efficient voxelized renderable neural 3D spatial representation that utilizes 3D Gaussian splatting. 3DSR leverages the strengths of both voxelization (memory efficiency) and 3D Gaussian splatting (high-quality image reconstruction). The proposed method achieves memory efficiency by reducing the number of 3D Gaussians in the 3D representation through voxelization, while preserving the image quality required for effective vision-based robotic applications. Experimental results demonstrate that 3DSR achieves over 90% of the best method’s reconstruction quality while requiring only 54.54% of its memory. Additional experiments on visual localization and navigation further confirm that the proposed method is readily applicable to robotics.