定向投递页 Focused Route

机器视觉方向 Machine Vision Track

光学机理、实验设计、模型指标都做过。 Hands-on work across optical mechanisms, experiments, and model metrics.

这一页面向机器视觉和图像算法岗位。重点放在图像恢复、Zemax 设计、训练评估和论文结果。 This page is for machine vision and image algorithm roles. It focuses on image restoration, Zemax design, training evaluation, and paper results.

能分析 PSF / OTF / MTF，并做图像恢复实验 Can analyze PSF / OTF / MTF and run image restoration experiments
使用 Python、PyTorch、Zemax 做训练和评估 Uses Python, PyTorch, and Zemax for training and evaluation
独立完成训练、消融、论文撰写和结果解释 Completed training, ablations, paper writing, and result interpretation independently

适合机器视觉、图像算法、光学算法、计算成像类岗位。 Best matched for machine vision, image algorithms, optical algorithms, and computational imaging roles.

下载该方向简历 Download this resume 联系我 Contact me

核心证据 Core Evidence

三组项目和经历。 Three project and experience groups.

同一批材料，按当前方向调整顺序。 The same material set is reordered for this direction.

论文与算法 Research & Algorithms 2025.03 - 2025.11

基于深度学习的单镜头退化图像恢复研究 Single-Lens Degraded Image Deblurring via Deep Learning

研究单镜头成像中的空间非均匀模糊和高频衰减。完成退化分析、数据构建、模型训练、指标评估和论文投稿。 Studied spatially variant blur and high-frequency loss in single-lens imaging. Completed degradation analysis, dataset creation, model training, evaluation, and paper submission.

用 Python 与 PyTorch 搭建两阶段去模糊流程，构建约 4800 组 blur-sharp 成对数据。 Built a two-stage deblurring pipeline in Python and PyTorch with roughly 4,800 blur-sharp pairs.
设计无归一化残差主干，引入多尺度重建损失、边缘一致性与低权重对抗学习。 Designed a non-normalized residual backbone with multi-scale reconstruction loss, edge consistency, and low-weight adversarial learning.
完成消融实验、指标评估与论文撰写，并以第一作者发表于 IEEE 国际会议。 Completed ablation studies, evaluation, and paper writing, then published the work as first author at an IEEE conference.

PSNR 33.19SSIM 0.9383LPIPS 0.0556+4.23 dB vs baseline

光学设计 Optical Design 2025.07

宇瞳杯微单镜头设计 Yutong Cup Mirrorless Lens Design

参与微单镜头光学系统设计。完成方案论证、Zemax 优化、公差分析和装配顺序设计。 Worked on a mirrorless lens optical system. Completed scheme review, Zemax optimization, tolerance analysis, and assembly planning.

采用反远距结构与双胶合透镜方案，围绕色差、场曲、彗差和畸变建立评价函数。 Used a retrofocus structure with doublets and built merit functions around chromatic aberration, field curvature, coma, and distortion.
完成 13 片镜头设计，含 2 片非球面镜片与 1 片保护玻璃。 Completed a 13-element design including 2 aspheric elements and 1 cover glass.
实现焦距 18.89mm、F/2.0、最大畸变 0.69%、总长 108.79mm，并完成鬼像抑制分析。 Reached 18.89 mm focal length, F/2.0, 0.69% max distortion, and 108.79 mm total length with ghost suppression analysis.

18.89 mmF/2.00.69% distortionMTF > 0.58 @ 40 lp/mm

成果证明 Recognition 2025.11

IEEE 论文与 Best Paper Honorable Award IEEE Paper & Best Paper Honorable Award

论文《Deblurring Single-Lens Degraded Images via Multi-Scale Modeling and Low-Weight Adversarial Learning》发表于 IEEE 国际会议，并获 ICAIRC 2025 Best Paper Honorable Award。 The paper “Deblurring Single-Lens Degraded Images via Multi-Scale Modeling and Low-Weight Adversarial Learning” was published at an IEEE conference and received ICAIRC 2025 Best Paper Honorable Award.

证明了我不仅能做实验，还能组织成完整研究表达。 Shows that I can not only run experiments but also shape them into complete research communication.
是机器视觉方向最直接的外部认可之一。 One of the strongest external signals for the machine vision track.
也能补充技术支持页面中的可信度证明。 Also strengthens credibility on the support-oriented page.

岗位判断 Role Fit

为什么这些经历对当前方向有效。 Why these experiences matter for this track.

能分析 PSF / OTF / MTF，并做图像恢复实验 Can analyze PSF / OTF / MTF and run image restoration experiments

使用 Python、PyTorch、Zemax 做训练和评估 Uses Python, PyTorch, and Zemax for training and evaluation

独立完成训练、消融、论文撰写和结果解释 Completed training, ablations, paper writing, and result interpretation independently

荣誉与证明 Recognition

奖学金、优秀学生和志愿服务证明。 Scholarship, outstanding student, and volunteer service records.

这些材料用于补充学习成绩、执行稳定性和现场服务经历。 These records support academic performance, reliable execution, and on-site service experience.

研究生一等奖学业奖学金 First-Class Graduate Scholarship

前 10% Top 10%

优秀学生 Outstanding Student

前 5% Top 5%

金钥匙一星志愿者 Golden Key Volunteer

投洽会志愿服务荣誉 Recognition for fair volunteer service

简历下载 Resume Pack

这一页的下一步动作已经准备好。 The next step for this track is ready.

下载这条岗位线的定向简历，然后直接通过邮箱联系我。如果希望继续用微信沟通，可以在邮件里备注，我会按投递场景提供。 Download the tailored resume for this track and contact me by email. If you prefer WeChat for the next conversation, mention it in the email and I will share the suitable contact method.

机器视觉方向 Machine Vision Track 下载 PDF Download PDF

联系我 Contact

简历和联系方式在这里。 Resume files and contact details are here.

邮箱 Email hezhichao08@163.com

微信沟通 WeChat 可在邮件中备注微信沟通，我会回传微信方式。 Mention WeChat in your email and I will share the best contact method.

发送邮件 Email me