快手计算机视觉算法工程师/专家(人像美化方向)(北京/深圳)
社招全职D1915地点:北京状态:招聘
任职要求
1、硕士及以上学历,计算机、数学相关专业优先; 2、熟悉GAN 、扩散模型、VAE等生成模型原理,在图像生成和多模态等领域有深入研究及相关产品落地者优先;熟悉图像处理算法基本原理,有人像美化、图像降噪/增强、超分等算法研发经验者优先; 3、具备扎实的编程功底,熟练使用 C ++/ Python 等至少一种编程语言,有ACM/IOI/知名算法竞赛获奖经历者优先; 4、在NIPS、ICML、CVPR、ICCV 、ECCV 、TPAMI等国际会议/期刊有论文发表者优先; 5、动手能力强,有技术追求,善于表达沟通和协同合作。
工作职责
1、负责AIGC人像图像的生成/编辑等算法研发,重点解决模型的生成质量、多样性、可控编辑等问题; 2、负责人像美化生成技术的前沿探索,包括但不限于人像美感提升、稳定性优化等,将前沿的CV技术与快手丰富的业务场景结合,被上亿用户所使用。
包括英文材料
学历+
图像处理+
https://opencv.org/blog/computer-vision-and-image-processing/
This fascinating journey involves two key fields: Computer Vision and Image Processing.
https://www.geeksforgeeks.org/python/image-processing-in-python/
Image processing involves analyzing and modifying digital images using computer algorithms.
https://www.youtube.com/watch?v=kSqxn6zGE0c
In this Introduction to Image Processing with Python, kaggle grandmaster Rob Mulla shows how to work with image data in python!
算法+
https://roadmap.sh/datastructures-and-algorithms
Step by step guide to learn Data Structures and Algorithms in 2025
https://www.hellointerview.com/learn/code
A visual guide to the most important patterns and approaches for the coding interview.
https://www.w3schools.com/dsa/
C+
https://www.freecodecamp.org/chinese/news/the-c-beginners-handbook/
本手册遵循二八定律。你将在 20% 的时间内学习 80% 的 C 编程语言。
https://www.youtube.com/watch?v=87SH2Cn0s9A
https://www.youtube.com/watch?v=KJgsSFOSQv0
This course will give you a full introduction into all of the core concepts in the C programming language.
https://www.youtube.com/watch?v=PaPN51Mm5qQ
In this complete C programming course, Dr. Charles Severance (aka Dr. Chuck) will help you understand computer architecture and low-level programming with the help of the classic C Programming language book written by Brian Kernighan and Dennis Ritchie.
Python+
https://liaoxuefeng.com/books/python/introduction/index.html
中文,免费,零起点,完整示例,基于最新的Python 3版本。
https://www.learnpython.org/
a free interactive Python tutorial for people who want to learn Python, fast.
https://www.youtube.com/watch?v=K5KVEU3aaeQ
Master Python from scratch 🚀 No fluff—just clear, practical coding skills to kickstart your journey!
https://www.youtube.com/watch?v=rfscVS0vtbw
This course will give you a full introduction into all of the core concepts in python.
ICML+
https://icml.cc/
CVPR+
https://cvpr.thecvf.com/
ICCV+
https://iccv.thecvf.com/
ICCV is the premier international computer vision event comprising the main conference and several co-located workshops and tutorials.
ECCV+
https://eccv.ecva.net/
ECCV is the official event under the European Computer Vision Association and is biannual on even numbered years.
相关职位
社招3年以上T9379
职位描述 1.从事图像处理、计算机视觉、模式识别等相关领域的算法研发; 2.负责视频、图像的智能人像效果研发,参与项目包括但不限于美颜、滤镜、特效、人脸算法、图像合成等; 3.对人像基础效果调试优化,极致呈现效果(如肤质、祛痘、脸型,体型等的美化); 4.结合AI技术与硬件特性完成需求落地以创新方案探索。
更新于 2023-08-03
社招3年以上研发类
作为核心算法成员,参与AI图像相关算法研发,主要服务于下一代智能相册系统。主要工作包括: 一、图像理解方向: 1)开发基于多模态语义的图像理解算法:人物识别、事件聚类、情绪识别、场景识别等;构建个性化的图像语义标签体系; 2)设计图像内容质量评估模型(重复、模糊、人脸表情等)提升用户体验; 3)探索RAG、多模态图像大模型、文本大模型联动下,agent能力建设和开发。 二、 图像AIGC方向(创作与编辑): 1)研究并实现图像生成与编辑算法,如背景替换、人像美化、风格迁移、文生图,图生图等; 2)参与基于 Diffusion基础模型训练; 3)参与ControlNet、Inpainting、aigc编辑大模型等前沿应用模型的业务开发和落地;