Search Results for author: Yibo Liu

Found 15 papers, 8 papers with code

VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving

no code implementations9 Jul 2024 Yibo Liu, Zheyuan Yang, Guile Wu, Yuan Ren, Kejian Lin, Bingbing Liu, Yang Liu, Jinjun Shan

In particular, we utilize a multi-expert Diffusion Models strategy to generate the structure information and employ a subject-driven structure-controlled generation mechanism to model appearance information.

Autonomous Driving Image to 3D +5

L-PR: Exploiting LiDAR Fiducial Marker for Unordered Low Overlap Multiview Point Cloud Registration

1 code implementation5 Jun 2024 Yibo Liu, Jinjun Shan, Amaldev Haridevan, Shuo Zhang, Kejian Lin

Then, we formulate the unordered multiview point cloud registration problem as a maximum a-posteriori (MAP) problem and develop a framework consisting of two levels of graphs to address it.

Point Cloud Registration

MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Driving

no code implementations ICCV 2023 Yibo Liu, Kelly Zhu, Guile Wu, Yuan Ren, Bingbing Liu, Yang Liu, Jinjun Shan

This set-level latent code is an expression of the optimal 3D shape in the implicit space, and can be subsequently decoded to a continuous SDF of the vehicle.

3D Reconstruction Autonomous Driving

Evolutionary Multitasking with Solution Space Cutting for Point Cloud Registration

no code implementations12 Dec 2022 Wu Yue, Peiran Gong, Maoguo Gong, Hangqi Ding, Zedong Tang, Yibo Liu, Wenping Ma, Qiguang Miao

However, most evolving registration methods cannot tackle the local optimum well and they have rarely investigated the success ratio, which implies the probability of not falling into local optima and is closely related to the practicality of the algorithm.

Point Cloud Registration Transfer Learning

Fiducial Tag Localization on a 3D LiDAR Prior Map

1 code implementation2 Sep 2022 Yibo Liu, Jinjun Shan, Hunter Schofield

We conduct both qualitative and quantitative experiments to demonstrate that our approach is the first method applicable to localize tags on a 3D LiDAR map while achieving better accuracy compared to previous methods.


Endowing Language Models with Multimodal Knowledge Graph Representations

1 code implementation27 Jun 2022 Ningyuan Huang, Yash R. Deshpande, Yibo Liu, Houda Alberts, Kyunghyun Cho, Clara Vania, Iacer Calixto

We use the recently released VisualSem KG as our external knowledge repository, which covers a subset of Wikipedia and WordNet entities, and compare a mix of tuple-based and graph-based algorithms to learn entity and relation representations that are grounded on the KG multimodal information.

Multilingual Named Entity Recognition named-entity-recognition +2

Intensity Image-based LiDAR Fiducial Marker System

1 code implementation3 Mar 2022 Yibo Liu, Hunter Schofield, Jinjun Shan

In this paper, an Intensity Image-based LiDAR Fiducial Marker (IILFM) system is developed.

Autonomous Vision-based UAV Landing with Collision Avoidance using Deep Learning

no code implementations17 Sep 2021 Tianpei Liao, Amal Haridevan, Yibo Liu, Jinjun Shan

There is a risk of collision when multiple UAVs land simultaneously without communication on the same platform.

Collision Avoidance

Application of Ghost-DeblurGAN to Fiducial Marker Detection

1 code implementation8 Sep 2021 Yibo Liu, Amaldev Haridevan, Hunter Schofield, Jinjun Shan

Feature extraction or localization based on the fiducial marker could fail due to motion blur in real-world robotic applications.

Deblurring Generative Adversarial Network +1

2D-CTC for Scene Text Recognition

no code implementations23 Jul 2019 Zhaoyi Wan, Fengming Xie, Yibo Liu, Xiang Bai, Cong Yao

Scene text recognition has been an important, active research topic in computer vision for years.

Decoder Scene Text Recognition +2

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