Search Results for author: Xinli Xu

Found 13 papers, 6 papers with code

MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detection

no code implementations7 Feb 2025 Zhiqiang Yang, Qiu Guan, Zhongwen Yu, Xinli Xu, Haixia Long, Sheng Lian, Haigen Hu, Ying Tang

Due to the effective multi-scale feature fusion capabilities of the Path Aggregation FPN (PAFPN), it has become a widely adopted component in YOLO-based detectors.

object-detection Object Detection

GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs

no code implementations15 Dec 2024 Xinli Xu, Wenhang Ge, Dicong Qiu, Zhifei Chen, Dongyu Yan, Zhuoyun Liu, Haoyu Zhao, HanFeng Zhao, Shunsi Zhang, Junwei Liang, Ying-Cong Chen

We demonstrate that 3D Gaussians with physical property annotations enable applications in physics-based dynamic simulation and robotic grasping.

Material Segmentation Robotic Grasping

PRM: Photometric Stereo based Large Reconstruction Model

no code implementations10 Dec 2024 Wenhang Ge, Jiantao Lin, Guibao Shen, Jiawei Feng, Tao Hu, Xinli Xu, Ying-Cong Chen

We propose PRM, a novel photometric stereo based large reconstruction model to reconstruct high-quality meshes with fine-grained local details.

model

LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images

no code implementations21 Oct 2024 Hao He, Yixun Liang, Luozhou Wang, Yuanhao Cai, Xinli Xu, Hao-Xiang Guo, Xiang Wen, Yingcong Chen

Recent large reconstruction models have made notable progress in generating high-quality 3D objects from single images.

3D Generation Image to 3D

FlexGen: Flexible Multi-View Generation from Text and Image Inputs

no code implementations14 Oct 2024 Xinli Xu, Wenhang Ge, Jiantao Lin, Jiawei Feng, Lie Xu, HanFeng Zhao, Shunsi Zhang, Ying-Cong Chen

We utilize the strong reasoning capabilities of GPT-4V to generate 3D-aware text annotations.

DuEDL: Dual-Branch Evidential Deep Learning for Scribble-Supervised Medical Image Segmentation

1 code implementation23 May 2024 Yitong Yang, Xinli Xu, Haigen Hu, Haixia Long, Qianwei Zhou, Qiu Guan

Despite the recent progress in medical image segmentation with scribble-based annotations, the segmentation results of most models are still not ro-bust and generalizable enough in open environments.

Decoder Image Segmentation +3

DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving

no code implementations CVPR 2024 Chen Min, Dawei Zhao, Liang Xiao, Jian Zhao, Xinli Xu, Zheng Zhu, Lei Jin, Jianshu Li, Yulan Guo, Junliang Xing, Liping Jing, Yiming Nie, Bin Dai

In this paper, we address this challenge by introducing a world model-based autonomous driving 4D representation learning framework, dubbed \emph{DriveWorld}, which is capable of pre-training from multi-camera driving videos in a spatio-temporal fashion.

3D Object Detection Motion Forecasting +4

Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting

1 code implementation10 Apr 2024 Hao Lu, Jiaqi Tang, Xinli Xu, Xu Cao, Yunpeng Zhang, Guoqing Wang, Dalong Du, Hao Chen, Yingcong Chen

Finally, for MC3D-Det joint training, the elaborate dataset merge strategy is designed to solve the problem of inconsistent camera numbers and camera parameters.

3D Object Detection Autonomous Driving +1

TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning

1 code implementation28 Dec 2022 Peixiang Huang, Li Liu, Renrui Zhang, Song Zhang, Xinli Xu, Baichao Wang, Guoyi Liu

In this paper, we propose the learning scheme of Target Inner-Geometry from the LiDAR modality into camera-based BEV detectors for both dense depth and BEV features, termed as TiG-BEV.

3D Object Detection object-detection

FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection

no code implementations22 Sep 2022 Xinli Xu, Shaocong Dong, Lihe Ding, Jie Wang, Tingfa Xu, Jianan Li

Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely relies on LiDAR point clouds for 3D proposal refinement.

3D Object Detection Autonomous Driving +2

Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

2 code implementations20 Jun 2022 Chen Min, Xinli Xu, Dawei Zhao, Liang Xiao, Yiming Nie, Bin Dai

This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE).

3D Object Detection 3D Semantic Segmentation +6

Cannot find the paper you are looking for? You can Submit a new open access paper.