Search Results for author:
Found 25 papers, 13 papers with code
HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDAR
To promote research of egocentric human interaction in large scenes and facilitate downstream tasks, we also present a dataset, containing 8 sequences in 4 large scenes (200 to 5, 000 $m^2$), providing 36k frames of accurate 4D human motions with SMPL annotations and dynamic scenes, 31k frames of cropped human point clouds, and scene mesh of the environment.
OC3D: Weakly Supervised Outdoor 3D Object Detection with Only Coarse Click Annotation
Experimental results on the widely used KITTI and nuScenes datasets demonstrate that our OC3D with only coarse clicks achieves state-of-the-art performance compared to weakly-supervised 3D detection methods.
L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection
However, the fusion of LiDAR and 4D radar is challenging because they differ significantly in terms of data quality and the degree of degradation in adverse weather.
FedSAC: Dynamic Submodel Allocation for Collaborative Fairness in Federated Learning
Second, to implement the BCF, we design a submodel allocation module with a theoretical guarantee of fairness.
Commonsense Prototype for Outdoor Unsupervised 3D Object Detection
The prevalent approaches of unsupervised 3D object detection follow cluster-based pseudo-label generation and iterative self-training processes.
FedPFT: Federated Proxy Fine-Tuning of Foundation Models
Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs.
RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method
Comprehensive capturing of human motions requires both accurate captures of complex poses and precise localization of the human within scenes.
Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection
LiDAR-based 3D object detection models have traditionally struggled under rainy conditions due to the degraded and noisy scanning signals.
LiSA: LiDAR Localization with Semantic Awareness
In SCR a scene is represented as a neural network which outputs the world coordinates for each point in the input point cloud.
HINTED: Hard Instance Enhanced Detector with Mixed-Density Feature Fusion for Sparsely-Supervised 3D Object Detection
Compared with leading sparsely-supervised methods HINTED significantly improves the detection performance on hard instances notably outperforming fully-supervised methods in detecting challenging categories like cyclists.
DiffLoc: Diffusion Model for Outdoor LiDAR Localization
We recognize APR's lack of robust features learning and iterative denoising process leads to suboptimal results.
SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration
To the best of our knowledge, our approach is the first to facilitate point cloud registration with skeletal geometric priors.
CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
The core of this dataset is a blending optimization process, which corrects for the pose as it drifts and is affected by the magnetic conditions.
SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments
We present SLOPER4D, a novel scene-aware dataset collected in large urban environments to facilitate the research of global human pose estimation (GHPE) with human-scene interaction in the wild.
Virtual Sparse Convolution for Multimodal 3D Object Detection
Finally, we develop a semi-supervised pipeline VirConv-S based on a pseudo-label framework.
SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization
In this work, we propose a novel LiDAR localization framework, SGLoc, which decouples the pose estimation to point cloud correspondence regression and pose estimation via this correspondence.
CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations
Combining CoIn with an iterative training strategy, we propose a CoIn++ pipeline, which requires only 2% annotations in the KITTI dataset to achieve performance comparable to the fully supervised methods.
Transformation-Equivariant 3D Object Detection for Autonomous Driving
However, it is difficult to apply such networks to 3D object detection in autonomous driving due to its large computation cost and slow reasoning speed.
LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds
Quantitative and qualitative experiments show that our method outperforms the techniques based only on RGB images.
Ranked #3 on
3D Human Pose Estimation
on SLOPER4D
(using extra training data)
HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR
We propose Human-centered 4D Scene Capture (HSC4D) to accurately and efficiently create a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, and rich interactions between humans and environments.
Federated Learning with Fair Averaging
Fairness has emerged as a critical problem in federated learning (FL).
Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling
Point2Node can dynamically explore correlation among all graph nodes from different levels, and adaptively aggregate the learned features.
RF-Net: An End-to-End Image Matching Network based on Receptive Field
This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images.
LO-Net: Deep Real-time Lidar Odometry
We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation.
Traffic Sign Timely Visual Recognizability Evaluation Based on 3D Measurable Point Clouds
Then, based on the VEM, we proposed the concept of the Visual Recognizability Field (VRF) to reflect the visual recognizability distribution in 3D space and established a Visual Recognizability Evaluation Model (VREM) to measure a traffic sign visual recognizability for a given viewpoint.
