Abstract The advancements in automatic text-to-3D generation have been remarkable. Most existing methods use pre-trained text-to-image diffusion models to optimize 3D representations like Neural Radia

Abstract Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural rad

Abstract We introduce SparseNeuS, a novel neural rendering based method for the task of surface reconstruction from multi-view images. This task becomes more difficult when only sparse images are prov

VSCode上用debugpy搭配time调试DDP程序由于不少任务并不是通过python直接启动的，尤其是使用slurm等方式调度的集群，由于机卡分离，难以直接从vscode启动调试；DDP由于其多进程的特性，调试起来也十分麻烦。debugpy与time搭配使用算是这种条件下一个不错的调试方案。 launch.json基本配置 1234567891011121314151617181920212

VSCode 自定义背景直接修改 workbench.desktop.main.css 固然简单，但每次 VSCode 自动更新都会重写核心源码，导致自定义样式丢失。而将自定义 CSS 抽离至外部独立文件，利用 Custom CSS and JS Loader 插件进行动态注入。更新后只需一键重载即可恢复。 提取自定义 CSS在本地安全路径（如用户目录 .vscode 下）新建 backgroun

Abstract An important paradigm of natural language processing consists of large-scale pre-training on general domain data and adaptation to particular tasks or domains. As we pre-train larger models,

利用移动硬盘作为MacBook的系统盘动机ROM是可以替换的，RAM是不可或缺的。 对macbook而言，在同样要多花不少钱的情况下，升级RAM显然比升级ROM性价比要高——毕竟ROM不足可以用移动硬盘解决，但移动硬盘也只能作为U盘一类的东西存贮文件，有些软件（比如AE）的缓存会占用系统不少空间，把这些文件夹放在移动硬盘内可能会导致软件找不到路径，在系统盘大小不够的情况下，将移动硬盘作为外置系统盘

Abstract We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. To perform novel view synthesis in this under-constrained setting, we capit

Abstract The ability to synthesize realistic and diverse indoor furniture layouts automatically or based on partial input, unlocks many applications, from better interactive 3D tools to data synthesis

Data Parallel And Distributed Data ParallelData ParallelProcedure Fig.1 Data Parallel 12345678While iterating: 1. Scatter batch to mini-batch and distribute them across given GPUs 2.