Human mesh reconstruction from a single image is challenging in the presence of occlusion, which can be 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 map dense human 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 SOTA methods on heavily occluded images and achieves comparable results on the standard benchmarks (3DPW).

翻译：从单张图像中进行人体网格重建在存在遮挡（包括自遮挡、物体遮挡或他人遮挡）时具有挑战性。现有方法要么无法准确分离人体特征，要么缺乏适当的特征补全监督。本文提出密集修复人体网格重建（DIMR）方法，这是一种利用密集对应图处理遮挡的两阶段方法。该方法采用密集对应图分离可见人体特征，并通过基于注意力的特征补全模块在结构化UV密集人体图上补全人体特征。我们还设计了一种特征修复训练过程，引导网络从未遮挡特征中学习。我们在多个数据集上评估了所提方法，并证明了其在严重遮挡场景下优于其他方法的卓越性能。大量实验表明，我们的方法在严重遮挡图像上明显优于先前的最优方法（SOTA），并在标准基准（3DPW）上取得了可比的结果。