songqikong / songqikong.github.io Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
https://songqikong.github.io/2023-10-07-2023-09-23-scoda-introduction/
Ⅰ. Abstract 3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g. 3D computer-aided design models. However, the domain gap between...
https://songqikong.github.io/2023-09-15-snowflakenet-introduction/
SnowflakeNet Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer, ICCV 2021 & TPAMI 2023
https://songqikong.github.io/2023-07-11-summer-train-record-1/?
Pytorch代码训练 & 深度学习问题的思考
https://songqikong.github.io/2023-10-07-multi-resource-interleaving/
Multi-Resource Interleaving for Deep Learning Training, SIGCOMM 2022 Ⅰ. Abstract Training Deep Learning (DL) model requires multiple resource types, including CPUs, GPUs, storage IO, and network IO. Advancements in DL have produced a wide spectrum of models that have diverse usage patterns on different resource types. Existing DL schedulers focus...
https://songqikong.github.io/2023-09-28-2023-09-23-scoda-introduction/
Ⅰ. Abstract 3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g. 3D computer-aided design models. However, the domain gap between...
issue
https://songqikong.github.io/2023-11-02-hdr/?
基于去噪和去量化的单幅图像HDR重建
https://songqikong.github.io/2023-07-10-summer-train-record-1/?
Pytorch代码训练 & 深度学习思考
https://songqikong.github.io/2023-09-28-scoda-introduction/
SCoDA:Domain Adaptive Shape Completion for Real Scans, CVPR 2023 Ⅰ. Abstract 3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g....
https://songqikong.github.io/2023-09-26-2023-09-23-scoda_introduction/
Ⅰ. Abstract 3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g. 3D computer-aided design models. However, the domain gap between...
https://songqikong.github.io/2023-11-05-ponderv2/
用通用预训练范式保存3D基础模型的方法
https://songqikong.github.io/2023-10-07-blossom-algorithm/
在图论中,最大加权匹配问题是一个经典的组合优化问题,通常用于求解二分图中的最佳匹配。下面我会解释一下这个问题的基本概念: 二分图(Bipartite Graph):一个图可以被分为两个不相交的集合,通常称为左集合和右集合,其中每个顶点都属于其中一个集合。如果图的每一条边都连接一个左集合中的顶点和一个右集合中的顶点,那么这个图就是一个二分图。 匹配(Matching):在一个二分图中,匹配是指一组不相交的边,它们的端点分别属于左集合和右集合,没有两条边共享同一个顶点。如果一个顶点属于某个匹配,那么它就被匹配了,否则它是未匹配的。 加权图(Weighted Graph):每条边都有一个关联的权重或成本。在最大加权匹配问题中,我们要找到一组边的匹配,使得这些边的权重之和最大。 最大加权匹配问题的目标是在给定的二分图中找到一种匹配方式,使得匹配的边的权重之和达到最大。这个问题可以用于各种实际应用,例如稳定婚姻问题、任务分配问题等。 让我们通过一个具体的例子来说明最大加权匹配问题。考虑以下二分图,其中有一些任务和工人,每个任务和工人之间都有一个特定的成本或权重,我们的目标是找到一种匹配方式,使得总成本最小化: 任务(左集合): A, B, C 工人(右集合): X, Y, Z 下面是每个任务和工人之间的成本: A - X: 2 A - Y: 3 A - Z: 4 B - X: 3 B - Y: 2 B - Z: 1 C - X: 5 C - Y: 1 C...
https://songqikong.github.io/2023-09-28-2023-09-23-scoda_introduction/
Ⅰ. Abstract 3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g. 3D computer-aided design models. However, the domain gap between...
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.