Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image
This work addresses the limitation of requiring depth sensors for broader applications in robotics and AR/VR, though it is incremental as it builds on existing category-level pose estimation methods.
The paper tackles the problem of category-level 6D object pose estimation from monocular RGB images by proposing OLD-Net, which predicts object-level depth and achieves state-of-the-art performance on CAMERA25 and REAL275 datasets.
Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications. In order to relieve this problem, this paper proposes a novel approach named Object Level Depth reconstruction Network (OLD-Net) taking only RGB images as input for category-level 6D object pose estimation. We propose to directly predict object-level depth from a monocular RGB image by deforming the category-level shape prior into object-level depth and the canonical NOCS representation. Two novel modules named Normalized Global Position Hints (NGPH) and Shape-aware Decoupled Depth Reconstruction (SDDR) module are introduced to learn high fidelity object-level depth and delicate shape representations. At last, the 6D object pose is solved by aligning the predicted canonical representation with the back-projected object-level depth. Extensive experiments on the challenging CAMERA25 and REAL275 datasets indicate that our model, though simple, achieves state-of-the-art performance.