【AI视野·今日CV 计算机视觉论文速览第233期】Tue, 3 Aug 2021

AI视野·今日CS.CV 计算机视觉论文速览
Tue, 3 Aug 2021
Totally xx papers
👉上期速览✈更多精彩请移步主页

在这里插入图片描述

Interesting:

📚****ReFormer, 用于图像标注的关系型transformer，可利用生成sense graph的关系图实现图像标注。(from 石溪分校)
在这里插入图片描述

获取的关系图已经图像标注结果：
在这里插入图片描述

📚****开放世界的实体分割任务, (from 香港中文)
We introduce a new image segmentation task, termed Entity Segmentation (ES) with the aim to segment all visual entities in an image without considering semantic category labels.
在这里插入图片描述

code: https://github.com/dvlab-research/Entity

📚***RigNet, 基于图像重复引导的稀疏深度稠密补全方法(from 南京理工PCA实验)
Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this completion. （克服模糊图像引导带来的问题）
在这里插入图片描述

📚综述Bridging Gap between Image Pixels and Semantics, (from USC)
The fact that there exists a gap between low-level features and semantic meanings of images, called the semantic gap, is known for decades. Resolution of the semantic gap is a long standing problem.
在这里插入图片描述

📚人像神经重光照, (from 上海科技大学)
在这里插入图片描述

📚DPT, 基于片元的可变形transformer(from 中科院自动化所)
在这里插入图片描述
利用DePatch替代了PVT中的patch embedding 模块。

code: https://github.com/CASIA-IVA-Lab/DPT

📚阴影/投影艺术的可差分渲染, (from IIT CVIG)
One such interesting application is Shadow Art - a unique form of sculptural art where 2D shadows cast by a 3D sculpture produce artistic effects. In this work, we revisit shadow art using differentiable render- ing based optimization frameworks to obtain the 3D sculp- ture from a set of shadow (binary) images and their corre- sponding projection information.生成特定视角下投影形状对于的三维mesh。
在这里插入图片描述

在这里插入图片描述

📚ManiSkill, 从描述中学习通用的操作技能的大规模机器人操作数据集。(from UCSD)
we focus on object-level generalization and propose SAPIEN Manipulation Skill Benchmark (abbreviated as ManiSkill), a large-scale learning-from-demonstrations benchmark for articulated object manipulation with visual input (point cloud and image)
在这里插入图片描述

code:ttps://github.com/haosulab/ManiSkill

📚单图失焦估计, (from 乐卓伯大学 au)
A guiding principle is that the level of blurriness due to defocus is related to the distance between the object and the focal plane. Based on this principle and the widely used assumption that Gaussian blur is a good model for defocus blur, we formulate the problem of estimating the spatially varying defocus blurriness as a Gaussian blur classification problem.
Applications in adaptive image enhancement, defocus magnification, and multi-focus image fusion.
在这里插入图片描述