We tackle the problem of single-image Human Mesh Recovery (HMR). Previous
approaches are mostly based on a single crop. In this paper, we shift the
single-crop HMR to a novel multiple-crop HMR paradigm. Cropping a human from
image multiple times by shifting and scaling the original bounding box is
feasible in practice, easy to implement, and incurs neglectable cost, but
immediately enriches available visual details. With multiple crops as input, we
manage to leverage the relation among these crops to extract discriminative
features and reduce camera ambiguity. Specifically, (1) we incorporate a
contrastive learning scheme to enhance the similarity between features
extracted from crops of the same human. (2) We also propose a crop-aware fusion
scheme to fuse the features of multiple crops for regressing the target mesh.
(3) We compute local cameras for all the input crops and build a
camera-consistency loss between the local cameras, which reward us with less
ambiguous cameras. Based on the above innovations, our proposed method
outperforms previous approaches as demonstrated by the extensive experiments.

本研究通过引入多裁剪方法，结合对裁剪间关系的分析以提取判别特征、减少相机不确定性，并利用对相同人体多裁剪的对比学习、特征融合和局部相机一致性等策略，改进了以往的单图像人体网格恢复方法。

在一张图像中使用对比学习和相机一致性进行多人体网格恢复

Multiple-Crop Human Mesh Recovery with Contrastive Learning and Camera  Consistency in A Single Image

Likelihood-free methods perform parameter inference in stochastic simulator
models where evaluating the likelihood is intractable but sampling synthetic
data is possible. One class of methods for this likelihood-free problem uses a
classifier to distinguish between pairs of parameter-observation samples
generated using the simulator and pairs sampled from some reference
distribution, which implicitly learns a density ratio proportional to the
likelihood. Another popular class of methods fits a conditional distribution to
the parameter posterior directly, and a particular recent variant allows for
the use of flexible neural density estimators for this task. In this work, we
show that both of these approaches can be unified under a general contrastive
learning scheme, and clarify how they should be run and compared.

该研究探讨了两种不需要概率似然函数的方法来处理具有随机模拟器模型的参数推断问题，分别是通过分类器学习隐含的密度比例和构建条件分布进行参数后验的灵活神经密度估计。研究表明这两种方法可以共同运行于一种对比学习策略下，并详细解释了它们如何运行和相互比较。