# Deep Model-Based 6D Pose Refinement in RGB Source: [Deep Model-Based 6D Pose Refinement in RGB]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:13:58.604Z Authors: Fabian Manhardt, Wadim Kehl, Nassir Navab, Federico Tombari Published: 2018-10-07T01:22:57.000Z ## Abstract We present a novel approach for model-based 6D pose refinement in color data. Building on the established idea of contour-based pose tracking, we teach a deep neural network to predict a translational and rotational update. At the core, we propose a new visual loss that drives the pose update by aligning object contours, thus avoiding the definition of any explicit appearance model. In contrast to previous work our method is correspondence-free, segmentation-free, can handle occlusion and is agnostic to geometrical symmetry as well as visual ambiguities. Additionally, we observe a strong robustness towards rough initialization. The approach can run in real-time and produces pose accuracies that come close to 3D ICP without the need for depth data. Furthermore, our networks are trained from purely synthetic data and will be published together with the refinement code to ensure reproducibility. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [6D Pose Estimation on LINEMOD 5 (test)](): 6D Pose Estimation; LINEMOD 5 (test); Avg Acc: 34.1. ## Original sources and implementation [Original paper]() [PDF]()