arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.09149cs.CV
收藏

采用区域感知循环损失的数字人手部合成自适应多模态控制

Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss

Queen Mary University of London(伦敦玛丽女王大学)

Qifan Fu, Xiaohang Yang, Muhammad Asad, Changjae Oh, Shanxin Yuan, Gregory Slabaugh

AI总结:

针对扩散模型生成数字人手部姿态失真问题,研究通过整理How2Sign数据集、引入自适应多模态融合及提出区域感知循环损失,有效提升了手部及整体姿态生成质量。

摘要:

扩散模型已展现出合成图像的卓越能力,包括生成特定姿势的人体。然而,当前模型在对精细手部姿态生成施加充分条件控制方面面临挑战,导致手部区域出现严重失真。为解决这一问题,我们首先对How2Sign数据集进行整理,提供更丰富、更准确的手部姿态标注。此外,我们引入自适应多模态融合,整合骨架、深度、表面法向量等不同模态所表征的人物物理特征。我们还提出了一种新颖的区域感知循环损失(Region-Aware Cycle Loss,RACL),使扩散模型训练能够聚焦于改善手部区域,从而提升生成手势的质量。具体而言,所提出的RACL计算生成图像的全身姿态关键点与真实值之间的加权关键点距离,在平衡整体姿态精度的同时生成更高质量的手部姿态。此外,我们采用两个手部区域指标——hand-PSNR和hand-Distance用于手部姿态生成评估。我们的实验评估证明了所提方法在提升扩散模型生成的数字人体姿态质量,尤其是手部区域质量方面的有效性。源代码可在https://github.com/fuqifan/Region-Aware-Cycle-Loss获取。

英文摘要:

Diffusion models have shown their remarkable ability to synthesize images, including the generation of humans in specific poses. However, current models face challenges in adequately expressing conditional control for detailed hand pose generation, leading to significant distortion in the hand regions. To tackle this problem, we first curate the How2Sign dataset to provide richer and more accurate hand pose annotations. In addition, we introduce adaptive, multi-modal fusion to integrate characters' physical features expressed in different modalities such as skeleton, depth, and surface normal. Furthermore, we propose a novel Region-Aware Cycle Loss (RACL) that enables the diffusion model training to focus on improving the hand region, resulting in improved quality of generated hand gestures. More specifically, the proposed RACL computes a weighted keypoint distance between the full-body pose keypoints from the generated image and the ground truth, to generate higher-quality hand poses while balancing overall pose accuracy. Moreover, we use two hand region metrics, named hand-PSNR and hand-Distance for hand pose generation evaluations. Our experimental evaluations demonstrate the effectiveness of our proposed approach in improving the quality of digital human pose generation using diffusion models, especially the quality of the hand region. The source code is available at https://github.com/fuqifan/Region-Aware-Cycle-Loss.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑