Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation

By Xingrui Yang, Hai Li, Hongjia Zhai, Yuhang Ming, Yuqian Liu, Guofeng Zhang. International Symposium on Mixed and Augmented Reality, 2022

295 citations recorded by the source corpus.

In this work, we present a dense tracking and mapping system named Vox-Fusion, which seamlessly fuses neural implicit representations with traditional volumetric fusion methods. Our approach is inspired by the recently developed implicit mapping and positioning system and further extends the idea so that it can be freely applied to practical scenarios. Specifically, we leverage a voxel-based neural implicit surface representation to encode and optimize the scene inside each voxel. Furthermore, we adopt an octree-based structure to divide the scene and support dynamic expansion, enabling our system to track and map arbitrary scenes without knowing the environment like in previous works. Moreover, we proposed a high-performance multi-process framework to speed up the method, thus supporting some applications that require real-time performance. The evaluation results show that our methods can achieve better accuracy and completeness than previous methods. We also show that our Vox-Fusion can be used in augmented reality and virtual reality applications. Our source code is publicly available at https://github.com/zju3dv/Vox-Fusion.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/80ba6fff6d24906d4dba698b0699d62b676f11fd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Geology

Deva Ramanan

Citations in the corpus

A Survey on 3D Gaussian Splatting (2024, unknown): “These approaches adopt a hybrid deformation strategy: linear blend skinning handles rigid skeletal transformations such as joint rotations, while pose-conditioned deformation fields account for secondary non-rigid effects like muscle jiggles.”
NeRF: Neural Radiance Field in 3D Vision, A Comprehensive Review (2022, unknown): “The segmentation loss forces point samples along rays through to the sky pixels to have zero density.”
SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (2023, background): “For the past three decades, SLAM research has extensively centered around the question of map representation – resulting in a variety of sparse [2, 3, 7, 23], dense [4, 6, 8, 13, 15, 25, 26, 34, 42, 43], and neural scene representations [21, 29, 30, 37, 46, 55].”
Recent advances in 3D Gaussian splatting (2024, unknown): “…with LiDAR point cloud and builds up an optimizable size-adaptive voxel Methods PSNR ↑ SSIM ↑ LPIPS ↓ NICE-SLAM [122] 24.42 0.81 0.23 Vox-Fusion [123] 24.41 0.80 0.24 Co-SLAM [124] 30.24 0.94 0.25 GS-SLAM [115] 31.56 0.97 0.094 SplaTAM [116] 34.11 0.97 0.10 GaussianSplattingSLAM [117] 37.50…”