Search papers, labs, and topics across Lattice.
This paper introduces GAP-GDRNet, a novel geometry-aware framework for monocular RGB-based 6D pose sensing specifically designed for challenging spacecraft images. By integrating an attention-based feature refinement module and a patch-level geometric self-attention mechanism, the model effectively enhances the stability of pose estimation despite issues like weak surface texture and occlusion. The results demonstrate significant improvements in pose accuracy, showcasing the framework's ability to leverage both global and local geometric cues in real-world scenarios.
Attention mechanisms can drastically improve pose sensing accuracy in the face of challenging visual conditions like occlusion and weak textures.
Monocular relative pose sensing is a central perception problem in non-cooperative rendezvous and on-orbit servicing. In spacecraft images, however, weak surface texture, thin appendages, illumination changes, and partial occlusion often leave only sparse and unstable geometric evidence. This article presents GAP-GDRNet, a geometry-aware attention-enhanced framework for monocular RGB-based 6D pose sensing. The method follows the geometry-guided direct regression paradigm of GDR-Net and modifies two points in the pipeline: an attention-based feature refinement (AFR) module is placed before dense geometric prediction, and a patch-level geometric self-attention (PGSA) module is inserted into Patch-PnP. AFR reinforces global spacecraft structure together with local weak-texture cues; PGSA then relates downsampled geometric patches before final pose regression. A Blender-based annotation process supplies target masks, visible-region masks, dense model-coordinate maps, camera intrinsics, and 6D pose labels for supervised training.
Tsinghua AI