SM$^3$: Self-Supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects

no code implementations • 17 Jan 2024 • Haowen Wang, Zhen Zhao, Zhao Jin, Zhengping Che, Liang Qiao, Yakun Huang, Zhipeng Fan, XIUQUAN QIAO, Jian Tang

Reconstructing real-world objects and estimating their movable joint structures are pivotal technologies within the field of robotics.

DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Field

no code implementations • 4 Aug 2023 • Haowen Wang, Zhipeng Fan, Zhen Zhao, Zhengping Che, Zhiyuan Xu, Dong Liu, Feifei Feng, Yakun Huang, XIUQUAN QIAO, Jian Tang

We introduce a pose regression module that shares the deformation features and template codes from the fields to estimate the accurate 6D pose of each object in the scene.

Object Pose Estimation

RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion

no code implementations • 6 Jun 2023 • Haowen Wang, Zhengping Che, Yufan Yang, Mingyuan Wang, Zhiyuan Xu, XIUQUAN QIAO, Mengshi Qi, Feifei Feng, Jian Tang

Raw depth images captured in indoor scenarios frequently exhibit extensive missing values due to the inherent limitations of the sensors and environments.

Depth Completion Transparent objects

RGB-Depth Fusion GAN for Indoor Depth Completion

no code implementations • CVPR 2022 • Haowen Wang, Mingyuan Wang, Zhengping Che, Zhiyuan Xu, XIUQUAN QIAO, Mengshi Qi, Feifei Feng, Jian Tang

In this paper, we design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map.

Depth Completion Transparent objects

ROGA: Random Over-sampling Based on Genetic Algorithm

no code implementations • 1 Jan 2021 • ZONGDA HAN, XIUQUAN QIAO, SHUBO ZHAN

Therefore, based on this problem, we propose an oversampling algorithm ROGA based on genetic algorithm.