Communitygithub.com

curiositech/windags-skills

激光雷达、点云和传感器融合的3D计算机视觉标注工具、工作流和AI辅助标注专家。涵盖SAM4D/Point-SAM、人在回路架构和垂直领域特定训练策略。

windags-skills 是什么?

该技能(curiositech/windags-skills)是面向3D计算机视觉标注领域的专家级指南,专门服务于自动驾驶、机器人、基础设施检测和地理空间应用中的激光雷达和点云数据。它提供了全面的工具选型分析,涵盖商业平台(如BasicAI、Supervisely)和开源方案(如CVAT),并深入讲解了SAM4D(ICCV 2025)和Point-SAM(ICLR 2025)等最新AI辅助标注架构。技能文档详细阐述了“模型在回路”的人机协作标注流水线,通过80/20规则和主动学习策略大幅提升效率。此外,它还系统比较了专用模型(如YOLO、PointPillars)与大视觉语言模型(VLM)在3D任务中的优劣,并给出了针对自动驾驶、基础设施巡检和农业/野火等垂直领域的最佳混合架构方案。该技能同时指出了常见反模式(如盲目使用SAM、跳过人工验证),并提供了工具选型决策树和参考资源,旨在帮助开发者和AI工程师避免陷阱,做出最优技术选择。

兼容平台~Claude Code~Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/3d-cv-labeling-2026

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

3D计算机视觉标注专家(2026)

针对自动驾驶、机器人、基础设施检测和地理空间应用中的激光雷达/点云计算机视觉,提供3D标注工具、AI辅助标注工作流和训练架构的专家指导。

何时使用此技能

✅ 适用于:

  • 选择3D点云标注工具(BasicAI、Supervisely、Segments.ai、Deepen AI)
  • 实现用于自动标注工作流的SAM4D/Point-SAM
  • 设计人在回路标注流水线
  • 传感器融合标注(相机 + 激光雷达 + 雷达)
  • 训练架构决策:专用模型 vs 视觉语言模型(VLM)
  • 垂直领域特定3D检测(自动驾驶、检测、农业、野火)

❌ 不适用于:

  • 无3D背景的2D图像标注(请使用clip-aware-embeddings或Label Studio文档)
  • 通用ML模型训练(请使用ml-engineer)
  • 不含点云的视频标注(请使用computer-vision-pipeline)
  • 视觉语言模型(VLM)提示工程(请使用prompt-engineer)
  • 摄影测量/3D重建(请使用地理处理工具)

2026年工具全景概览

商业领先工具

工具优势最佳适用场景关键AI特性
BasicAI一键检测自动驾驶专为自动驾驶汽车微调的预标注模型
Supervisely定制化研发团队AI追踪、2D→3D一键标注
Segments.ai2D+3D同步机器人感知连续帧传播
Deepen AI传感器标定内部感知团队像素级精准多传感器
Dataloop企业级MLOps大型标注团队模型辅助 + 点云聚焦
Encord完整工作流多模态项目追踪ID管理
Ango Hub (iMerit)密集标注复杂多模态帧间传播

开源选项

工具成熟度限制
CVAT稳定仅支持3D包围框,插值能力有限
3D BAT良好全环绕标注,半自动追踪
Label Studio部分3D支持更适合多格式,非专精3D

面向3D的SAM演进(2024-2026)

SAM4D(ICCV 2025)- 多模态 + 时序

关键创新:统一多模态位置编码(UMPE)将相机和激光雷达在共享的3D空间中对齐。

相机流 → 特征提取 → ┐
                      ├→ UMPE对齐 → 可提示3D分割
激光雷达流 → 点编码 → ┘

数据引擎突破:自动伪标签生成速度比人工标注快100倍以上,方法包括:

  1. 视觉基础模型(VFM)驱动的视频掩码片段
  2. 时空4D重建
  3. 跨模态掩码片段融合

数据集:Waymo-4DSeg(30万+相机-激光雷达对齐的掩码片段)

Point-SAM(ICLR 2025)- 原生3D提示

架构:专门为点云设计的高效Transformer(非从2D改编)。

知识蒸馏:将2D SAM蒸馏为3D Point-SAM,通过数据引擎生成:

  • 部件级伪标签
  • 对象级伪标签

基准测试:在室内(ScanNet)和室外(nuScenes、Waymo)数据集上超越现有最佳方法。

SAMNet++(2025)- 混合流水线

两阶段方法:

  1. SAM执行无监督分割
  2. 改编的PointNet++进行语义精度细化

最佳适用:无人机工作流,其中L1激光雷达+RGB相机提供了带色彩的点云。


人在回路架构

模型在回路范式(2023-2026)

旧方法:人工标注 → 训练模型 → 部署 新方法:模型辅助 → 人工验证 → 快速迭代

┌─────────────────────────────────────────────────────────┐
│                       标注流水线                          │
├─────────────────────────────────────────────────────────┤
│  原始数据 → AI预标注 → 人工审核 → 质量检查               │
│     │           │              │             │          │
│     │     SAM4D/VLM      仅在AI不       一致性         │
│     │     生成提案       确定处修正       抽样          │
└─────────────────────────────────────────────────────────┘

效率提升

方法1万帧耗时标注质量
仅手动400小时95%(专家级)
AI预标注+审核50小时97%(AI+人工)
SAM4D数据引擎4小时92%(伪标签)

80/20法则:约80%的机器学习项目时间花在数据准备上。模型在回路方法大幅削减了这一时间。

质量保证策略

  1. 一致性抽样:对子集进行多人标注,衡量一致性
  2. 主动学习:将不确定的预测分配给专家
  3. 分级审核:第1级(关键对象)由领域专家验证,第2/3级使用AI置信度阈值

为什么针对3D任务,专用训练优于视觉语言模型(VLM)

核心权衡

方面专用模型(YOLO、PointPillars)视觉语言模型(GPT-4V、Gemini)
延迟10-50毫秒(实时)500-2000毫秒
3D精度强几何先验文本-3D对齐噪声大
新对象闭集(仅训练过的)开放词汇
计算可边缘部署需要GPU集群
幻觉无(确定性)有(安全关键风险)
领域偏移应对困难(雾、夜晚)泛化能力更好

何时使用各方案

使用专用模型当:

  • 需要实时推理(自动驾驶、机器人)
  • 已知对象类别(基础设施缺陷、作物类型)
  • 安全关键部署(无法容忍幻觉)
  • 边缘部署(无人机、嵌入式系统)

使用视觉语言模型/基础模型当:

  • 对新领域进行零样本探索
  • 生成训练数据(弱标签)
  • 需要开放词汇能力(“找出所有损坏的”)
  • 进行领域自适应引导

混合架构(2025+最佳实践)

                    ┌───────────────────────┐
                    │   VLM(慢脑)         │
                    │  • 场景理解           │
                    │  • 开放词汇           │
                    │  • 异常检测           │
                    └──────────┬────────────┘
                               │ 高层上下文
                               ▼
┌──────────────────────────────────────────────────────────┐
│              专用检测器(快脑)                           │
│  • 实时推理(YOLO、PointPillars、CenterPoint)          │
│  • 已知对象检测与追踪                                   │
│  • 安全关键决策                                         │
└──────────────────────────────────────────────────────────┘

示例:

  • VOLTRON:YOLOv8 + LLaMA2 用于危害识别
  • DrivePI:点云 + 多视角 + 语言指令(0.5B Qwen2.5)

垂直领域特定训练架构

基础设施检测

对象:电线杆、绝缘子、导线、植被、损伤类型 传感器融合:RGB + 热成像 + 激光雷达 训练数据需求:

  • 热异常样本(不同温度)
  • 损伤分类(裂纹、腐蚀、锈蚀等级)
  • 植被净空测量

架构:

激光雷达 → 点云编码器 → ┐
热成像 → 2D编码器     → ├→ 融合 → 多任务头
RGB → 2D编码器         → ┘          ├→ 对象检测
                                      ├→ 缺陷分类
                                      └→ 净空回归

自动驾驶

对象:车辆、行人、骑行者、交通标志、车道标线 关键需求:时序一致性(跨帧的追踪ID) 训练数据需求:

  • 长尾场景(紧急车辆、动物、碎片)
  • 恶劣天气(雾、雨、雪、夜晚)
  • 边缘情况(施工区、事故)

架构:使用鸟瞰图(BEV)表示的CenterPoint、PointPillars或体素检测器。

农业/野火

对象:作物行、树冠高度、燃料负荷、火势蔓延边界 传感器融合:RGB + 多光谱 + 激光雷达 训练数据需求:

  • 作物生长阶段
  • 疾病/害虫视觉特征
  • 基于激光雷达冠层高度模型(CHM)的燃料负荷密度

为什么不只用视觉语言模型? 视觉语言模型无法:

  • 测量精确高度(激光雷达回归)
  • 在高光谱波长下分类
  • 为处方图保持空间精度

常见反模式

反模式:"凡事务用SAM"

新手思维:"SAM可以分割一切,所以我直接把它用在激光雷达数据上"

现实:

  • SAM 1/2 是2D模型——它们不理解3D几何
  • 点云需要Point-SAM或SAM4D
  • 直接应用会产生不含几何先验的噪声掩码

正确方法:使用Point-SAM进行原生3D分割,或将点云投影到2D供SAM使用,再提升回3D。

反模式:跳过人工验证

新手思维:"AI预标注准确率达到95%,我们可以跳过审核"

现实:

  • 10万对象上5%的误差 = 5000个错误标签
  • 错误在边缘情况下会累积(恰恰是你需要准确性的地方)
  • 模型会学习复现标注错误

正确方法:第1级(安全关键)始终人工验证。第2/3级使用置信度阈值。

反模式:用视觉语言模型做实时推理

新手思维:"GPT-4V可以识别我照片中的损坏"

现实:

  • 每帧延迟500-2000毫秒
  • 无法在边缘设备上运行
  • 在安全关键场景中存在幻觉风险

正确方法:使用视觉语言模型进行数据生成/探索,使用专用模型进行部署。

反模式:单模态训练

新手思维:"激光雷达足以进行3D检测"

现实:

  • 激光雷达:精确几何,无颜色/纹理
  • 相机:丰富语义,无深度
  • 融合方法的mAP优于单模态5-15%

正确方法:从一开始就采用传感器融合。SAM4D展示了融合伪标签优于单模态。


决策树:选择你的方案

                    是否需要实时推理?
                          /            \
                       是              否
                        |                |
                使用专用检测器        是探索性任务?
                (YOLO、CenterPoint)  /        \
                        |            是          否
                   有标注数据?       |           |
                      /    \    使用视觉语言   使用SAM4D
                    是      否    模型进行     生成伪标签
                    |        |    零样本
                训练模型  使用SAM4D/
                         Point-SAM
                         进行自动标注

工具选型决策矩阵

需求推荐工具
大规模自动驾驶Deepen AI 或 BasicAI
研发/研究灵活性Supervisely 或 Segments.ai
多模态(相机+激光雷达+雷达)Ango Hub 或 Dataloop
自托管/开源CVAT + 3D插件 或 3D BAT
机器人感知Segments.ai(2D+3D同步)
预算有限Label Studio + 自定义脚本

参考资料

  • /references/sam4d-architecture.md - SAM4D UMPE 和数据引擎深度解析
  • /references/tool-comparison-matrix.md - 所有工具的详细功能对比
  • /references/hybrid-architecture-examples.md - VOLTRON、DrivePI 实现模式
  • /references/vertical-training-recipes.md - 基础设施、自动驾驶、农业特定细节

来源

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

curiositech/windags-skills

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

curiositech/windags-skills

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

curiositech/windags-skills

Implement WCAG 2.2 AA/AAA compliance with automated testing, keyboard navigation, screen reader support, and focus management. Activate on: accessibility audit, WCAG compliance, keyboard navigation, screen reader, aria attributes, axe-core, focus trap. NOT for: design-level accessibility review (use design-accessibility-auditor), color contrast only (use css-in-js-architect).

curiositech/windags-skills

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.

curiositech/windags-skills

Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.

curiositech/windags-skills

>- Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

curiositech/windags-skills

Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.

curiositech/windags-skills

Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).

curiositech/windags-skills

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

curiositech/windags-skills

AI-powered calendar management and agent-based scheduling coordination. Covers calendar APIs (Google Calendar, CalDAV/iCal), AI scheduling assistants (Reclaim, Clockwise, Motion, Cal.com), building custom calendar agents with MCP, multi-calendar merging, timezone management, focus block protection, meeting fatigue detection, and agent-to-agent meeting negotiation protocols. Activate on: "calendar agent", "AI scheduling", "calendar coordination", "meeting scheduling", "calendar API", "focus time protection", "calendar optimization", "Google Calendar MCP", "Reclaim", "Clockwise", "Motion", "Cal.com", "smart scheduling", "calendar-aware agent", "timezone scheduling", "agent negotiation meetings". NOT for: manual calendar UI component design (use form-validation-architect), project management scheduling or Gantt charts (use project-management-guru-adhd), general time-tracking or pomodoro apps (use adhd-daily-planner for time-awareness), building the agent itself from scratch (use agent-creator).

curiositech/windags-skills

Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

curiositech/windags-skills

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

curiositech/windags-skills

Automated discovery and matching of agent skills for dynamic task routing and capability assessment

curiositech/windags-skills

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

curiositech/windags-skills

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Deep comparison of A2A protocol, MCP, OpenAI function calling, and LangChain message types. Teaches when to use rigid schemas vs free-form with validation, typed vs untyped, streaming vs batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

curiositech/windags-skills

Logic-based agent programming language implementing BDI architecture for practical autonomous agent development

curiositech/windags-skills

>- Design AgentSpeak(L)-style BDI agents with context-guarded plans, selection functions, and intention stacks. Use for interruptible autonomy, agent policy, and multi-agent orchestration in dynamic environments. NOT for simple rule engines, static planners, or centralized workflows.

curiositech/windags-skills

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

curiositech/windags-skills

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications.

curiositech/windags-skills

license: Apache-2.0 NOT for unrelated tasks outside this domain.

相关技能