CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge

no code implementations • 24 Feb 2024 • Xiao Lin, Minghao Zhu, Ronghao Dang, Guangliang Zhou, Shaolong Shu, Feng Lin, Chengju Liu, Qijun Chen

Inspired by this motivation, we propose CLIPose, a novel 6D pose framework that employs the pre-trained vision-language model to develop better learning of object category information, which can fully leverage abundant semantic knowledge in image and text modalities.

Contrastive Learning Language Modelling +2

TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer

no code implementations • 25 Oct 2023 • Xiao Lin, Deming Wang, Guangliang Zhou, Chengju Liu, Qijun Chen

To improve robustness to occlusion, we adopt Transformer to perform the exchange of global information, making each local feature contains global information.

6D Pose Estimation using RGB Object

RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing

no code implementations • 19 Sep 2023 • Jiahang Li, Yikang Zhang, Peng Yun, Guangliang Zhou, Qijun Chen, Rui Fan

Additionally, we release SYN-UDTIRI, the first large-scale road scene parsing dataset that contains over 10, 407 RGB images, dense depth images, and the corresponding pixel-level annotations for both freespace and road defects of different shapes and sizes.

Decoder Scene Parsing