# Dense Human Body Correspondences Using Convolutional Networks Source: [Dense Human Body Correspondences Using Convolutional Networks]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:23:26.300Z Authors: Lingyu Wei, Qixing Huang, Duygu Ceylan, Etienne Vouga, Hao Li Published: 2015-11-18T18:36:54.000Z ## Abstract We propose a deep learning approach for finding dense correspondences between 3D scans of people. Our method requires only partial geometric information in the form of two depth maps or partial reconstructed surfaces, works for humans in arbitrary poses and wearing any clothing, does not require the two people to be scanned from similar viewpoints, and runs in real time. We use a deep convolutional neural network to train a feature descriptor on depth map pixels, but crucially, rather than training the network to solve the shape correspondence problem directly, we train it to solve a body region classification problem, modified to increase the smoothness of the learned descriptors near region boundaries. This approach ensures that nearby points on the human body are nearby in feature space, and vice versa, rendering the feature descriptor suitable for computing dense correspondences between the scans. We validate our method on real and synthetic data for both clothed and unclothed humans, and show that our correspondences are more robust than is possible with state-of-the-art unsupervised methods, and more accurate than those found using methods that require full watertight 3D geometry. ## 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. - [Partial-to-full correspondence on FAUST (test)](): Partial-to-full correspondence; FAUST (test); AE (cm): 10.91. - [Partial-to-full correspondence on SHREC'19 (test)](): Partial-to-full correspondence; SHREC'19 (test); AE (cm): 17.24. - [Occlusion Detection on SMPL Inter-Subject (test)](): Occlusion Detection; SMPL Inter-Subject (test); AP: 32.25. - [Dense Correspondence Search on SMPL Inter-Subject (test)](): Dense Correspondence Search; SMPL Inter-Subject (test); EPE (non-occluded): 18.03. - [Occlusion Detection on SMPL Intra-Subject (test)](): Occlusion Detection; SMPL Intra-Subject (test); Average Precision: 32.2. - [Occlusion Detection on The Relightables Intra-Subject (test)](): Occlusion Detection; The Relightables Intra-Subject (test); AP: 25.78. - [Occlusion Detection on RenderPeople Intra-Subject (test)](): Occlusion Detection; RenderPeople Intra-Subject (test); AP: 34.13. - [Dense Correspondence Search on SMPL Intra-Subject (test)](): Dense Correspondence Search; SMPL Intra-Subject (test); EPE (non-occluded): 18.08. - [Dense Correspondence Search on Relightables Intra-Subject (test)](): Dense Correspondence Search; Relightables Intra-Subject (test); EPE (Non-Occluded): 29.54. - [Dense Correspondence Search on RenderPeople Intra-Subject (test)](): Dense Correspondence Search; RenderPeople Intra-Subject (test); EPE (Non-Occluded): 34.42. ## Original sources and implementation [Original paper]() [PDF]()