Differentiable rendering-based pose-conditioned human image generation
Differentiable rendering-based pose-conditioned human image generation
复制标题
基于可微渲染的姿势条件人类图像生成
DOI：
10.1109/cvprw53098.2021.00437
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Hiroshi Ishikawa
中科院分区：
文献类型：
--
作者：
Yusuke Horiuchi;Edgar Simo-Serra;Satoshi Iizuka;Hiroshi Ishikawa
有条件的人体图像生成，或者基于一个或多个参考图像生成具有指定姿势的人体图像，本质上是一个定义不明确的问题，因为参考图像中被遮挡的部分可能存在多个看似合理的外观。使用多个图像可以缓解这个问题，同时提高性能。在这项工作中，我们引入了一种可微分的顶点和边缘渲染器，用于合并姿势信息，以实现基于多个参考图像的人体图像生成。可微渲染器具有可以与系统其他部分联合优化的参数，以便通过学习更有意义的人体姿势形状表示来获得更好的结果。我们在 Market-1501 和 DeepFashion 数据集上评估我们的方法，并与现有方法进行比较，验证了我们方法的有效性。
Conditional human image generation, or generation of human images with specified pose based on one or more reference images, is an inherently ill-defined problem, as there can be multiple plausible appearance for parts that are occluded in the reference. Using multiple images can mitigate this problem while boosting the performance. In this work, we introduce a differentiable vertex and edge renderer for incorporating the pose information to realize human image generation conditioned on multiple reference images. The differentiable renderer has parameters that can be jointly optimized with other parts of the system to obtain better results by learning more meaningful shape representation of human pose. We evaluate our method on the Market-1501 and DeepFashion datasets and comparison with existing approaches validates the effectiveness of our approach.