We present the Minigrid and Miniworld libraries which provide a suite of
goal-oriented 2D and 3D environments. The libraries were explicitly created
with a minimalistic design paradigm to allow users to rapidly develop new
environments for a wide range of research-specific needs. As a result, both
have received widescale adoption by the RL community, facilitating research in
a wide range of areas. In this paper, we outline the design philosophy,
environment details, and their world generation API. We also showcase the
additional capabilities brought by the unified API between Minigrid and
Miniworld through case studies on transfer learning (for both RL agents and
humans) between the different observation spaces. The source code of Minigrid
and Miniworld can be found at this https URL,
Miniworld} along with their documentation at this https URL,
miniworld}.farama.org/.

介绍了 Minigrid 和 Miniworld 库，它们提供了一套目标导向的 2D 和 3D 环境，旨在让用户快速开发出适用于各种研究需求的新环境，两个库都被 RL 社区广泛采用，促进了在广泛领域内的研究。通过案例研究展示了 Minigrid 和 Miniworld 统一 API 带来的额外功能，并且该论文介绍了它们的设计哲学、环境细节和世界生成 API。

面向目标导向任务的模块化、可定制的增强学习环境：Minigrid 和 Miniworld

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning  Environments for Goal-Oriented Tasks

Vision Transformers (ViTs) have proven to be effective, in solving 2D image
understanding tasks by training over large-scale image datasets; and meanwhile
as a somehow separate track, in modeling the 3D visual world too such as voxels
or point clouds. However, with the growing hope that transformers can become
the "universal" modeling tool for heterogeneous data, ViTs for 2D and 3D tasks
have so far adopted vastly different architecture designs that are hardly
transferable. That invites an (over-)ambitious question: can we close the gap
between the 2D and 3D ViT architectures? As a piloting study, this paper
demonstrates the appealing promise to understand the 3D visual world, using a
standard 2D ViT architecture, with only minimal customization at the input and
output levels without redesigning the pipeline. To build a 3D ViT from its 2D
sibling, we "inflate" the patch embedding and token sequence, accompanied with
new positional encoding mechanisms designed to match the 3D data geometry. The
resultant "minimalist" 3D ViT, named Simple3D-Former, performs surprisingly
robustly on popular 3D tasks such as object classification, point cloud
segmentation and indoor scene detection, compared to highly customized
3D-specific designs. It can hence act as a strong baseline for new 3D ViTs.
Moreover, we note that pursing a unified 2D-3D ViT design has practical
relevance besides just scientific curiosity. Specifically, we demonstrate that
Simple3D-Former naturally enables to exploit the wealth of pre-trained weights
from large-scale realistic 2D images (e.g., ImageNet), which can be plugged in
to enhancing the 3D task performance "for free".

本文提出一种通用的视觉转换器（Visual Transformer），名为 Simple3D-Former，可用于高效地进行 2D 和 3D 任务的训练和预测，并且相比高度定制的 3D 特有设计实现了惊人的鲁棒性，同时利用大规模现实 2D 图像的预训练权重可免费提高 3D 任务的性能.

从 2D 视觉 Transformer 开始解决 3D 视觉任务？

Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?

We propose a generative model of 2D and 3D natural textures with diversity,
visual fidelity and at high computational efficiency. This is enabled by a
family of methods that extend ideas from classic stochastic procedural
texturing (Perlin noise) to learned, deep, non-linearities. The key idea is a
hard-coded, tunable and differentiable step that feeds multiple transformed
random 2D or 3D fields into an MLP that can be sampled over infinite domains.
Our model encodes all exemplars from a diverse set of textures without a need
to be re-trained for each exemplar. Applications include texture interpolation,
and learning 3D textures from 2D exemplars.

文中介绍一种高计算效率的生成 2D 和 3D 自然纹理的深度学习方法，可用于纹理插值和从 2D 纹理中学习 3D 纹理。