Fig. 4
From: Enhancing object pose estimation for RGB images in cluttered scenes
rotation network consists of two modules Multi-head Self-attention(MHSA) and the Iterative Refinement modules.
Fig. 4 | Scientific Reports
From: Enhancing object pose estimation for RGB images in cluttered scenes
rotation network consists of two modules Multi-head Self-attention(MHSA) and the Iterative Refinement modules.
