4 citations · 12 across the 8 of their papers we have counts for
11 papers
UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation
Daikun Liu, Xin Zhan, Teng Wang +2
We propose UniDynamics, a diffusion-based framework for future 4D dynamic scenes (RGB, depth, and optical flow) generation from a single event-RGB pair, without requiring long hist…
Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation
Daikun Liu, Teng Wang, Changyin Sun
Event cameras hold excellent dynamic properties, showing great potential for monocular depth estimation (MDE). However, existing methods mainly improve performance by optimizing co…
ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination
Teng Wang, Xinxin Zhao, Wenzhe Cai +1
Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent methods have leveraged Large La…
A Modern Look at Simplicity Bias in Image Classification Tasks
Xiaoguang Chang, Teng Wang, Changyin Sun
The simplicity Bias (SB) of neural networks, i.e.\ their tendency to represent simple functions, is a key factor in their generalization capabilities. Recent studies show that an e…
EDCFlow: Exploring Temporally Dense Difference Maps for Event-based Optical Flow Estimation
Daikun Liu, Lei Cheng, Teng Wang +1
Recent learning-based methods for event-based optical flow estimation utilize cost volumes for pixel matching but suffer from redundant computations and limited scalability to high…
Window-to-Window BEV Representation Learning for Limited FoV Cross-View Geo-localization
Lei Cheng, Teng Wang, Lingquan Meng +1
Cross-view geo-localization confronts significant challenges due to large perspective changes, especially when the ground-view query image has a limited field of view with unknown…
LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition
Teng Wang, Lingquan Meng, Lei Cheng +1
Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various fe…
Empowering Large Language Models on Robotic Manipulation with Affordance Prompting
Guangran Cheng, Chuheng Zhang, Wenzhe Cai +3
While large language models (LLMs) are successful in completing various language processing tasks, they easily fail to interact with the physical world by generating control sequen…
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
Wenzhang Liu, Wenzhe Cai, Kun Jiang +7
In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore. XuanCe of…
DGMem: Learning Visual Navigation Policy without Any Labels by Dynamic Graph Memory
Wenzhe Cai, Teng Wang, Guangran Cheng +2
In recent years, learning-based approaches have demonstrated significant promise in addressing intricate navigation tasks. Traditional methods for training deep neural network navi…
Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill
Wenzhe Cai, Siyuan Huang, Guangran Cheng +4
Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first…