Publications (18)
Keyframe-Based Feed-Forward Visual Odometry
Weichen Dai, Wenhan Su, Da Kong +2
The emergence of visual foundation models has revolutionized visual odometry~(VO) and SLAM, enabling pose estimation and dense reconstruction within a single feed-forward network.…
Multi-Spectral Visual Odometry without Explicit Stereo Matching
Weichen Dai, Yu Zhang, Donglei Sun +2
Multi-spectral sensors consisting of a standard (visible-light) camera and a long-wave infrared camera can simultaneously provide both visible and thermal images. Since thermal ima…
SLC-SLAM: Semantic-guided Loop Closure using Shared Latent Code for NeRF SLAM
Yuhang Ming, Di Ma, Weichen Dai +4
Targeting the notorious cumulative drift errors in NeRF SLAM, we propose a Semantic-guided Loop Closure using Shared Latent Code, dubbed SLC-SLAM. We argue that latent codes st…
RGB-D SLAM in Dynamic Environments Using Point Correlations
Weichen Dai, Yu Zhang, Ping Li +2
In this paper, a simultaneous localization and mapping (SLAM) method that eliminates the influence of moving objects in dynamic environments is proposed. This method utilizes the c…
VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning
Yuhang Ming, Minyang Xu, Xingrui Yang +5
Visual place recognition (VPR) is an essential component of many autonomous and augmented/virtual reality systems. It enables the systems to robustly localize themselves in large-s…
Enhance Accuracy: Sensitivity and Uncertainty Theory in LiDAR Odometry and Mapping
Zeyu Wan, Yu Zhang, Bin He +4
Currently, the improvement of LiDAR poses estimation accuracy is an urgent need for mobile robots. Research indicates that diverse LiDAR points have different influences on the acc…
COEFF-KANs: A Paradigm to Address the Electrolyte Field with KANs
Xinhe Li, Zhuoying Feng, Yezeng Chen +4
To reduce the experimental validation workload for chemical researchers and accelerate the design and optimization of high-energy-density lithium metal batteries, we aim to leverag…
A Multi-spectral Dataset for Evaluating Motion Estimation Systems
Weichen Dai, Yu Zhang, Shenzhou Chen +2
Visible images have been widely used for motion estimation. Thermal images, in contrast, are more challenging to be used in motion estimation since they typically have lower resolu…
Rotational Symmetry based Object Pose Estimation from Point Clouds in the Absence of Known 3D Models
Weichen Dai, Ruixun Yu, Yangjie Tang +4
Object pose estimation is crucial to many industrial applications, with one example being automated spray painting using a robot. However, confidentiality concerns often limit acce…
KALE-LM-Chem: Vision and Practice Toward an AI Brain for Chemistry
Weichen Dai, Yezeng Chen, Zijie Dai +9
Recent advancements in large language models (LLMs) have demonstrated strong potential for enabling domain-specific intelligence. In this work, we present our vision for building a…
HG3-NeRF: Hierarchical Geometric, Semantic, and Photometric Guided Neural Radiance Fields for Sparse View Inputs
Zelin Gao, Weichen Dai, Yu Zhang
Neural Radiance Fields (NeRF) have garnered considerable attention as a paradigm for novel view synthesis by learning scene representations from discrete observations. Nevertheless…
Spontaneous Spatial Cognition Emerges during Egocentric Video Viewing through Non-invasive BCI
Weichen Dai, Yuxuan Huang, Li Zhu +10
Humans possess a remarkable capacity for spatial cognition, allowing for self-localization even in novel or unfamiliar environments. While hippocampal neurons encoding position and…
CUS-GS: A Compact Unified Structured Gaussian Splatting Framework for Multimodal Scene Representation
Yuhang Ming, Chenxin Fang, Xingyuan Yu +4
Recent advances in Gaussian Splatting based 3D scene representation have shown two major trends: semantics-oriented approaches that focus on high-level understanding but lack expli…
3D Scene-Camera Representation with Joint Camera Photometric Optimization
Weichen Dai, Kangcheng Ma, Jiaxin Wang +4
Representing scenes from multi-view images is a crucial task in computer vision with extensive applications. However, inherent photometric distortions in the camera imaging can sig…
MInD: Improving Multimodal Sentiment Analysis via Multimodal Information Disentanglement
Weichen Dai, Xingyu Li, Zeyu Wang +4
Learning effective joint representations has been a central task in multi-modal sentiment analysis. Previous works addressing this task focus on exploring sophisticated fusion tech…
Exploring The Neural Burden In Pruned Models: An Insight Inspired By Neuroscience
Zeyu Wang, Weichen Dai, Xiangyu Zhou +2
Vision Transformer and its variants have been adopted in many visual tasks due to their powerful capabilities, which also bring significant challenges in computation and storage. C…
AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition
Yuhang Ming, Jian Ma, Xingrui Yang +3
We present AEGIS-Net, a novel indoor place recognition model that takes in RGB point clouds and generates global place descriptors by aggregating lower-level color, geometry featur…
RLDBF: Enhancing LLMs Via Reinforcement Learning With DataBase FeedBack
Weichen Dai, Zijie Dai, Zhijie Huang +6
While current large language models (LLMs) demonstrate remarkable linguistic capabilities through training on massive unstructured text corpora, they remain inadequate in leveragin…