We tackle the problem of sampling from intractable high-dimensional density
functions, a fundamental task that often appears in machine learning and
statistics. We extend recent sampling-based approaches that leverage controlled
stochastic processes to model approximate samples from these target densities.
The main drawback of these approaches is that the training objective requires
full trajectories to compute, resulting in sluggish credit assignment issues
due to use of entire trajectories and a learning signal present only at the
terminal time. In this work, we present Diffusion Generative Flow Samplers
(DGFS), a sampling-based framework where the learning process can be tractably
broken down into short partial trajectory segments, via parameterizing an
additional "flow function". Our method takes inspiration from the theory
developed for generative flow networks (GFlowNets), allowing us to make use of
intermediate learning signals and benefit from off-policy exploration
capabilities. Through a variety of challenging experiments, we demonstrate that
DGFS results in more accurate estimates of the normalization constant than
closely-related prior methods.

我们提出了一种基于扩散生成流采样器 (DGFS) 的抽样框架，该方法可以将学习过程易于处理地分解为短的部分轨迹段，通过参数化额外的 “流函数”，并且在各种具有挑战性的实验中展示了相比于相关先前方法更准确的规范常量估计。

扩散生成流采样器：通过部分轨迹优化改善学习信号

Diffusion Generative Flow Samplers: Improving learning signals through  partial trajectory optimization

Unlike images which are represented in regular dense grids, 3D point clouds
are irregular and unordered, hence applying convolution on them can be
difficult. In this paper, we extend the dynamic filter to a new convolution
operation, named PointConv. PointConv can be applied on point clouds to build
deep convolutional networks. We treat convolution kernels as nonlinear
functions of the local coordinates of 3D points comprised of weight and density
functions. With respect to a given point, the weight functions are learned with
multi-layer perceptron networks and density functions through kernel density
estimation. The most important contribution of this work is a novel
reformulation proposed for efficiently computing the weight functions, which
allowed us to dramatically scale up the network and significantly improve its
performance. The learned convolution kernel can be used to compute
translation-invariant and permutation-invariant convolution on any point set in
the 3D space. Besides, PointConv can also be used as deconvolution operators to
propagate features from a subsampled point cloud back to its original
resolution. Experiments on ModelNet40, ShapeNet, and ScanNet show that deep
convolutional neural networks built on PointConv are able to achieve
state-of-the-art on challenging semantic segmentation benchmarks on 3D point
clouds. Besides, our experiments converting CIFAR-10 into a point cloud showed
that networks built on PointConv can match the performance of convolutional
networks in 2D images of a similar structure.

本文介绍了一种新的卷积操作 PointConv，此操作可用于处理 3D 点云并建立深度卷积神经网络，该网络具有创建非线性函数权重和密度函数的功能，实验表明，PointConv 可用于挑战性的语义分割基准测试，并在 2D 图像的结构相似情况下提供类似于卷积网络的性能。

PointConv：3D 点云上的深度卷积网络

PointConv: Deep Convolutional Networks on 3D Point Clouds

We consider the problem of learning object arrangements in a 3D scene. The
key idea here is to learn how objects relate to human poses based on their
affordances, ease of use and reachability. In contrast to modeling
object-object relationships, modeling human-object relationships scales
linearly in the number of objects. We design appropriate density functions
based on 3D spatial features to capture this. We learn the distribution of
human poses in a scene using a variant of the Dirichlet process mixture model
that allows sharing of the density function parameters across the same object
types. Then we can reason about arrangements of the objects in the room based
on these meaningful human poses. In our extensive experiments on 20 different
rooms with a total of 47 objects, our algorithm predicted correct placements
with an average error of 1.6 meters from ground truth. In arranging five real
scenes, it received a score of 4.3/5 compared to 3.7 for the best baseline
method.

本研究基于物体的易用性、可达性和相对人体姿态的关系，通过 3D 空间特征和 Dirichlet 过程混合模型学习场景中不同物体相对人体姿态的分布情况，并以此作为推理对象，通过合适的密度函数，预测物体在房间中的正确放置位置。实验证明，与最佳基线方法相比，该算法的平均误差小于 1.6 米，分数达到 4.3/5。