Due to the lack of camera parameter information for in-the-wild images,
existing 3D human pose and shape (HPS) estimation methods make several
simplifying assumptions: weak-perspective projection, large constant focal
length, and zero camera rotation. These assumptions often do not hold and we
show, quantitatively and qualitatively, that they cause errors in the
reconstructed 3D shape and pose. To address this, we introduce SPEC, the first
in-the-wild 3D HPS method that estimates the perspective camera from a single
image and employs this to reconstruct 3D human bodies more accurately. First,
we train a neural network to estimate the field of view, camera pitch, and roll
given an input image. We employ novel losses that improve the calibration
accuracy over previous work. We then train a novel network that concatenates
the camera calibration to the image features and uses these together to regress
3D body shape and pose. SPEC is more accurate than the prior art on the
standard benchmark (3DPW) as well as two new datasets with more challenging
camera views and varying focal lengths. Specifically, we create a new
photorealistic synthetic dataset (SPEC-SYN) with ground truth 3D bodies and a
novel in-the-wild dataset (SPEC-MTP) with calibration and high-quality
reference bodies. Both qualitative and quantitative analysis confirm that
knowing camera parameters during inference regresses better human bodies. Code
and datasets are available for research purposes at this https URL

SPEC 是第一个在野外图像中从单幅图像估计透视相机并更准确地重构 3D 人体的 3D 人体姿态和形状方法，SPEC 通过训练神经网络来估计视场角、相机俯仰角和滚转角，并将相机标定与图像特征连接起来，一起用于回归 3D 人体的形状和姿势，其结果在标准基准和两个新的数据集中表现比之前的艺术更加准确。

使用估计相机在野外识别人物

SPEC: Seeing People in the Wild with an Estimated Camera

We present results on the inspiral, merger, and post-merger evolution of a
neutron star - neutron star (NSNS) system. Our results are obtained using the
hybrid pseudospectral-finite volume Spectral Einstein Code (SpEC). To test our
numerical methods, we evolve an equal-mass system for $\approx 22$ orbits
before merger. This waveform is the longest waveform obtained from fully
general-relativistic simulations for NSNSs to date. Such long (and accurate)
numerical waveforms are required to further improve semi-analytical models used
in gravitational wave data analysis, for example the effective one body models.
We discuss in detail the improvements to SpEC's ability to simulate NSNS
mergers, in particular mesh refined grids to better resolve the merger and
post-merger phases. We provide a set of consistency checks and compare our
results to NSNS merger simulations with the independent BAM code. We find
agreement between them, which increases confidence in results obtained with
either code. This work paves the way for future studies using long waveforms
and more complex microphysical descriptions of neutron star matter in SpEC.

本文使用 SpEC 进行中子星 - 中子星 (NSNS) 系统的 inspiral、合并和后合并演化的研究，着重讨论了 SpEC 模拟 NSNS 合并的改进和波形对比验证，并表明这些长波形为进一步改进重力波数据分析半解析模型提供了必要的支持。