Estimating 6D poses of objects is an essential computer vision task. However,
most conventional approaches rely on camera data from a single perspective and
therefore suffer from occlusions. We overcome this issue with our novel
multi-view 6D pose estimation method called MV6D which accurately predicts the
6D poses of all objects in a cluttered scene based on RGB-D images from
multiple perspectives. We base our approach on the PVN3D network that uses a
single RGB-D image to predict keypoints of the target objects. We extend this
approach by using a combined point cloud from multiple views and fusing the
images from each view with a DenseFusion layer. In contrast to current
multi-view pose detection networks such as CosyPose, our MV6D can learn the
fusion of multiple perspectives in an end-to-end manner and does not require
multiple prediction stages or subsequent fine tuning of the prediction.
Furthermore, we present three novel photorealistic datasets of cluttered scenes
with heavy occlusions. All of them contain RGB-D images from multiple
perspectives and the ground truth for instance semantic segmentation and 6D
pose estimation. MV6D significantly outperforms the state-of-the-art in
multi-view 6D pose estimation even in cases where the camera poses are known
inaccurately. Furthermore, we show that our approach is robust towards dynamic
camera setups and that its accuracy increases incrementally with an increasing
number of perspectives.

提出了一种名为 MV6D 的多视角 6D 姿态估计方法，该方法使用多个视角的 RGB-D 图像，通过 DenseFusion 层融合每个视角的图像，可以精确预测杂乱场景中所有对象的 6D 姿态.

MV6D: 使用深度点投票网络的 RGB-D 框架多视角 6D 位姿估计

MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network

Here, we present an end-to-end method to create 2D animation for a goalkeeper
attempting to block a penalty kick, and then correct that motion using an
iterative nonlinear optimization scheme. The input is a raw video that is fed
into pose and object detection networks to find the skeleton of the goalkeeper
and the ball. The output is a set of key frames of the skeleton associated with
the corrected motion so that if the goalkeeper missed the ball, the animation
will show then successfully deflecting it. Our method is robust enough correct
different kinds of mistakes the goalkeeper can make, such as not lunging far
enough or jumping to the incorrect side. Our method is also meant to be
semantically similar to the goalkeeper's original motion, which helps keep our
animation grounded with respect to actual human behavior.

提出了一种用于为扑救射门的门将创建 2D 动画并使用迭代非线性优化方案纠正该动作的端到端方法，以便于保持动画的语义相似性和实际人类行为相关性。

通过迭代非线性优化和动画进行语义运动校正

Semantic Motion Correction Via Iterative Nonlinear Optimization and Animation

We present an online approach to efficiently and simultaneously detect and
track the 2D pose of multiple people in a video sequence. We build upon Part
Affinity Field (PAF) representation designed for static images, and propose an
architecture that can encode and predict Spatio-Temporal Affinity Fields (STAF)
across a video sequence. In particular, we propose a novel temporal topology
cross-linked across limbs which can consistently handle body motions of a wide
range of magnitudes. Additionally, we make the overall approach recurrent in
nature, where the network ingests STAF heatmaps from previous frames and
estimates those for the current frame. Our approach uses only online inference
and tracking, and is currently the fastest and the most accurate bottom-up
approach that is runtime invariant to the number of people in the scene and
accuracy invariant to input frame rate of camera. Running at $\sim$30 fps on a
single GPU at single scale, it achieves highly competitive results on the
PoseTrack benchmarks.

本文提出了一种在线方法，可以有效地同时检测和跟踪视频序列中多个人的 2D 姿态，使用基于 PAF 表示的 STAF 编码和预测跨越视频序列的时间和空间亲和力场，使用递归神经网络使总体方法递归化，并且只使用在线推断和跟踪，不随场景中人数的运行时不变性和输入帧率的准确性不变性，使单 GPU 上的运行速度为约 30fps， 在 PoseTrack 基准测试中取得了极具竞争力的结果。