A Pose Proposal and Refinement Network for Better 6D Object Pose Estimation
| Autor: | Mohamed Chaabane, Ameni Trabelsi, Ross Beveridge, Nathaniel Blanchard |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
0209 industrial biotechnology
Computer science business.industry 02 engineering and technology Pipeline (software) 020901 industrial engineering & automation Discriminative model Feature (computer vision) Component (UML) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Representation (mathematics) business Pose Encoder Block (data storage) |
| Zdroj: | WACV |
| Popis: | In this paper, we present a novel, end-to-end 6D object pose estimation method that operates on RGB inputs. Our approach is composed of 2 main components: the first component classifies the objects in the input image and proposes an initial 6D pose estimate through a multi-task, CNN-based encoder/multi-decoder module. The second component, a refinement module, includes a renderer and a multi-attentional pose refinement network, which iteratively refines the estimated poses by utilizing both appearance features and flow vectors. Our refiner takes advantage of the hybrid representation of the initial pose estimates to predict the relative errors with respect to the target poses. It is further augmented by a spatial multi-attention block that emphasizes objects’ discriminative feature parts. Experiments on three benchmarks for 6D pose estimation show that our proposed pipeline outperforms state-of-the-art RGB-based methods with competitive runtime performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|