no code implementations • 19 Mar 2024 • Hongjia Zhai, Hai Li, Xingrui Yang, Gan Huang, Yuhang Ming, Hujun Bao, Guofeng Zhang
In this paper, we introduce Vox-Fusion++, a multi-maps-based robust dense tracking and mapping system that seamlessly fuses neural implicit representations with traditional volumetric fusion techniques.
1 code implementation • 15 Dec 2023 • Yuhang Ming, Jian Ma, Xingrui Yang, Weichen Dai, Yong Peng, Wanzeng Kong
We evaluate our AEGIS-Net on the ScanNetPR dataset and compare its performance with a pre-deep-learning feature-based method and five state-of-the-art deep-learning-based methods.
no code implementations • 4 Aug 2023 • Weihan Wang, Jiani Li, Yuhang Ming, Philippos Mordohai
Our method incorporates an Error-state Kalman Filter (ESKF) to estimate gyroscope bias and correct rotation estimates from monocular SLAM, overcoming dependence on pure monocular SLAM for rotation estimation.
1 code implementation • 28 Oct 2022 • Xingrui Yang, Hai Li, Hongjia Zhai, Yuhang Ming, Yuqian Liu, Guofeng Zhang
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.
no code implementations • 16 Sep 2022 • Yuhang Ming, Weicai Ye, Andrew Calway
The neural implicit mapper is trained on-the-fly, while though the neural tracker is pretrained on the ScanNet dataset, it is also finetuned along with the training of the neural implicit mapper.
1 code implementation • 18 Jul 2022 • Weicai Ye, Xingyuan Yu, Xinyue Lan, Yuhang Ming, Jinyu Li, Hujun Bao, Zhaopeng Cui, Guofeng Zhang
We present a novel dual-flow representation of scene motion that decomposes the optical flow into a static flow field caused by the camera motion and another dynamic flow field caused by the objects' movements in the scene.
1 code implementation • CVPR 2023 • Weicai Ye, Xinyue Lan, Shuo Chen, Yuhang Ming, Xingyuan Yu, Hujun Bao, Zhaopeng Cui, Guofeng Zhang
We present PVO, a novel panoptic visual odometry framework to achieve more comprehensive modeling of the scene motion, geometry, and panoptic segmentation information.
no code implementations • 25 Mar 2022 • Xingrui Yang, Yuhang Ming, Zhaopeng Cui, Andrew Calway
It is well known that visual SLAM systems based on dense matching are locally accurate but are also susceptible to long-term drift and map corruption.
1 code implementation • 4 Feb 2022 • Yuhang Ming, Xingrui Yang, Guofeng Zhang, Andrew Calway
We describe a novel approach to indoor place recognition from RGB point clouds based on aggregating low-level colour and geometry features with high-level implicit semantic features.
1 code implementation • 5 Aug 2021 • Yuhang Ming, Xingrui Yang, Andrew Calway
During the map construction, we use a pre-trained neural network to detect objects and estimate 6D poses from RGB-D data.