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 1702.02258cs.CVcs.AIcs.MMstat.ML
收藏

与2D联合检测一致的人体3D姿态的多个不同假设的生成

Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detections

Johns Hopkins University(约翰斯·霍普金斯大学)

Ehsan Jahangiri, Alan L. Yuille

摘要:

我们提出了一种方法来生成多个不同的和有效的人体姿态假设在3D中的所有一致的2D检测的关节在单目RGB图像。我们使用一种新的生成模型均匀(无偏)的空间解剖学合理的3D构成。我们的模型是组合的(通过组合部分产生姿势),并且由于它仅受解剖约束的限制,因此它可以推广到每个合理的人类3D姿势。去除模型偏差本质上有助于生成更多样化的3D姿势假设。我们认为,产生多个姿势假设是更合理的,而不是只产生一个单一的三维姿势的基础上的2D联合检测给定的深度模糊性和不确定性,由于闭塞和不完善的2D联合检测。我们希望,产生多个一致的姿势假设的想法可以引起一个新的线的未来的工作,在文献中还没有得到太多的关注。我们使用Human3.6M数据集进行实证评估。

英文摘要:

We propose a method to generate multiple diverse and valid human pose hypotheses in 3D all consistent with the 2D detection of joints in a monocular RGB image. We use a novel generative model uniform (unbiased) in the space of anatomically plausible 3D poses. Our model is compositional (produces a pose by combining parts) and since it is restricted only by anatomical constraints it can generalize to every plausible human 3D pose. Removing the model bias intrinsically helps to generate more diverse 3D pose hypotheses. We argue that generating multiple pose hypotheses is more reasonable than generating only a single 3D pose based on the 2D joint detection given the depth ambiguity and the uncertainty due to occlusion and imperfect 2D joint detection. We hope that the idea of generating multiple consistent pose hypotheses can give rise to a new line of future work that has not received much attention in the literature. We used the Human3.6M dataset for empirical evaluation.

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。

↑