发表机构
Linköping University（林雪平大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出CQF-HMR方法，采用受四元数约束的连续归一化流，从单张图像实现概率3D人体网格恢复，在Human3.6M等数据集上取得先进结果。
AI 中文摘要
从单张2D图像恢复3D数字人类是一个不适定的计算机视觉问题，原因在于深度信息的缺失。概率3D人体姿态估计通过生成模型从先验分布估计一组3D假设，以此弥补这一缺陷。然而，大多数现有工作仅关注3D关键点，这往往会产生不合理的姿态，难以应用于动画或数字人类等下游任务。基于SMPL的方法由于具有显式身体先验而具备更强的可扩展性，但由于关节旋转的非加性性质，其生成过程需要更复杂的建模。在本研究中，我们提出了一种新方法，用于在2D姿态估计的条件下，使用受四元数约束的连续归一化流来进行概率3D人体建模。我们提出的四元数流相较于使用其他旋转表示的方法具有显著优势。实验表明，我们的方法在Human3.6M数据集上取得了最先进的结果，尤其是在模糊场景中，并且在具有挑战性的3DPW和EMDB基准上取得了相当的姿态估计精度。
英文摘要
Recovering 3D digital humans from a single 2D image is an ill-posed computer vision problem due to the loss of depth information. Probabilistic 3D human pose estimation compensates for this by estimating a set of 3D hypotheses from a prior distribution via generative models. However, most prior work focuses only on 3D keypoints, which often leads to implausible poses that are difficult to apply to downstream tasks, e.g. animation or digital humans. SMPL-based methods are more scalable thanks to the explicit body priors, but it requires more complex modeling of the generation process due to the non-additive nature of the joint rotations. In this work, we propose a novel approach for probabilistic 3D humans using quaternion-constrained continuous normalizing flows conditioned on 2D pose estimations. Our proposed quaternion flows show significant advantages over approaches using other rotation representations. Experiments demonstrate state-of-the-art results of our method on Human3.6M, particularly in ambiguous settings, and comparable pose estimation accuracy on challenging 3DPW and EMDB benchmarks.
CommentsUnder submission
