Learning Dense UV Completion for 3D Human Mesh Recovery

Human mesh reconstruction from a single image is a challenging task due to the occlusion caused by self, objects, or other humans. Existing methods either fail to separate human features accurately or lack proper supervision for feature completion. In this paper, we propose Dense Inpainting Human Mesh Recovery (DIMR), a two-stage method that leverages dense correspondence maps to handle occlusion. Our method utilizes a dense correspondence map to separate visible human features and completes human features on a structured UV space with an attention-based feature completion module. We also design a feature inpainting training procedure that guides the network to learn from unoccluded features. We evaluate our method on several datasets and demonstrate its superior performance under heavily occluded scenarios compared to other methods. Extensive experiments show that our method obviously outperforms prior methods on heavily occluded images and achieves comparable results on the standard benchmarks. Moreover, our method is comparable with previous methods on no heavily occluded images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.