feat: add scripts for fetching arXiv papers and generating structured reviews

- Implemented `fetch_crowdroom_papers.py` to scrape arXiv papers related to CrowdRoom with customizable query topics and output options.
- Created `gen_review_from_json.py` to render structured markdown reviews from search results JSON, including statistics and insights on papers and GitHub repositories.
- Developed `search_info.py` for thematic searches on arXiv and GitHub, supporting HTTP/SOCKS5 proxies and structured output.

research/tools/gen_review_from_json.py

@@ -0,0 +1,303 @@
+"""把 search_results.json 渲染成结构化 markdown 综述。
+
+用法：
+    python3 research/gen_review_from_json.py \
+        --in research/search_results.json \
+        --out research/zed2i_arxiv_live_review.md
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+from collections import Counter
+from datetime import datetime
+
+
+# 主题中英文标签 + 项目阶段映射
+TOPIC_META = {
+    "stereo_matching": {
+        "zh": "A. 双目立体匹配（被动深度）",
+        "stage": "M2-3 / M3-4",
+        "intro": "对应 ZED 双目深度算法的替换/超越路线。关注零样本泛化、Transformer 架构、神经几何编码。",
+    },
+    "visual_inertial_slam": {
+        "zh": "B. 视觉惯性 SLAM / VIO",
+        "stage": "M2-1 / M3-3",
+        "intro": "对标 ZED 内建 VIO 的替代方案。关注 IMU 融合、长时鲁棒、动态环境。",
+    },
+    "gaussian_splatting_slam": {
+        "zh": "C. 3D Gaussian Splatting SLAM（融合建图）",
+        "stage": "M3-5 / M4",
+        "intro": "把 3DGS 作为 SLAM 后端，实现实时定位+建图+渲染一体化。world model 训练的核心视觉表征。",
+    },
+    "monocular_depth_foundation": {
+        "zh": "D. 单目深度基础模型",
+        "stage": "M3-4",
+        "intro": "Depth Anything / Marigold / Metric3D / UniDepth 等通用深度模型，作为双目深度失效的兜底。",
+    },
+    "indoor_rgbd_dataset": {
+        "zh": "E. 室内 RGB-D 数据集与重建",
+        "stage": "M4-1 / M4-2",
+        "intro": "可参考的数据集设计、评测基准、室内几何重建方法。",
+    },
+    "world_model_video": {
+        "zh": "F. 视频世界模型（下游应用）",
+        "stage": "M4-4",
+        "intro": "本项目数据 pipeline 的最终下游：训练能预测未来视频/动作的 world model。",
+    },
+    "zed_camera": {
+        "zh": "G. ZED 相机相关应用工作",
+        "stage": "全周期",
+        "intro": "用 ZED 系列采集数据的应用论文，参考其采集协议、评测方式、参数配置。",
+    },
+    "orbbec_gemini": {
+        "zh": "H. Orbbec / Femto / Azure Kinect 相关工作",
+        "stage": "国产化 / 替代硬件",
+        "intro": "奥比中光、乐视/微视 Femto、微软 Azure Kinect 等 RGB-D 相机的应用论文。",
+    },
+    "rgbd_indoor_reconstruction": {
+        "zh": "I. RGB-D 室内重建",
+        "stage": "M2-2 / M3-5",
+        "intro": "RGB-D 输入下的室内场景重建，与本项目的房间级建图任务高度对齐。",
+    },
+    "neural_stereo_depth": {
+        "zh": "J. 神经立体深度（指定 RAFT/IGEV/Foundation 家族）",
+        "stage": "M3-4",
+        "intro": "针对 RAFT-Stereo / IGEV-Stereo / FoundationStereo 等核心立体匹配方法的衍生与改进。",
+    },
+}
+
+CN_KEYWORDS = [
+    # 中国机构关键词（用于粗筛"国产团队"论文）
+    "tsinghua", "peking", "fudan", "shanghai jiao", "zhejiang", "ustc", "huazhong",
+    "harbin", "tianjin", "wuhan", "xi'an jiaotong", "xi'an", "nanjing",
+    "chinese academy", "cas ", "casia",
+    "hkust", "cuhk", "hku", "polyu", "city university of hong kong",
+    "alibaba", "tencent", "bytedance", "baidu", "huawei", "megvii",
+    "sensetime", "ant group", "didi", "meituan", "xiaomi",
+    "damo", "noah", "arc lab", "shanghai ai lab",
+]
+
+
+def is_china_team(authors: list[str], summary: str) -> bool:
+    """粗略判断是否有国产团队作者（依赖摘要中机构提及）。"""
+    lower = (" ".join(authors) + " " + summary).lower()
+    return any(k in lower for k in CN_KEYWORDS)
+
+
+def fmt_authors(authors: list[str], max_n: int = 4) -> str:
+    if not authors:
+        return "（作者信息缺失）"
+    if len(authors) <= max_n:
+        return ", ".join(authors)
+    return ", ".join(authors[:max_n]) + f" 等 ({len(authors)} 人)"
+
+
+def render_paper(p: dict, idx: int) -> list[str]:
+    aid = p.get("arxiv_id", "")
+    title = p.get("title", "").strip().rstrip(".")
+    pub = p.get("published", "")[:10]
+    authors = p.get("authors", [])
+    summary = p.get("summary", "")
+    cats = p.get("categories", [])
+    url = p.get("url") or f"https://arxiv.org/abs/{aid}"
+
+    china_tag = " 🇨🇳" if is_china_team(authors, summary) else ""
+
+    lines = [
+        f"#### {idx}. [{aid}]({url}) — {title}{china_tag}",
+        f"- **发表**: {pub}  |  **分类**: {', '.join(cats[:3]) if cats else '-'}",
+        f"- **作者**: {fmt_authors(authors)}",
+        f"- **摘要**: {summary}",
+        "",
+    ]
+    return lines
+
+
+def render_topic(topic: str, papers: list[dict]) -> list[str]:
+    meta = TOPIC_META.get(topic, {"zh": topic, "stage": "-", "intro": ""})
+    out = [
+        f"## {meta['zh']}",
+        f"**项目阶段**: {meta['stage']}  |  **论文数**: {len(papers)}",
+        "",
+        meta["intro"],
+        "",
+    ]
+
+    # 按时间排序（新到旧）
+    papers_sorted = sorted(papers, key=lambda p: p.get("published", ""), reverse=True)
+
+    for i, p in enumerate(papers_sorted, 1):
+        out.extend(render_paper(p, i))
+
+    return out
+
+
+def render_github_topic(topic: str, repos: list[dict]) -> list[str]:
+    out = [f"### GitHub: {topic}（按 stars 排序）", ""]
+    for r in repos:
+        out.append(
+            f"- [{r['name']}]({r['url']}) — ⭐ {r['stars']:,} | "
+            f"{r.get('language', '-')} | {r.get('description', '')[:120]}"
+        )
+    out.append("")
+    return out
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--in", dest="inp", default="research/data/search_results.json")
+    ap.add_argument("--out", default="research/spatial-memory/zed2i_arxiv_live_review.md")
+    args = ap.parse_args()
+
+    with open(args.inp, "r", encoding="utf-8") as f:
+        data = json.load(f)
+
+    arxiv = data.get("arxiv", {})
+    github = data.get("github", {})
+    meta = data.get("meta", {})
+
+    # 统计
+    total_papers = sum(len(v) for v in arxiv.values())
+    total_repos = sum(len(v) for v in github.values())
+
+    all_papers = [p for ps in arxiv.values() for p in ps]
+    china_papers = [p for p in all_papers if is_china_team(p.get("authors", []), p.get("summary", ""))]
+    cat_counter: Counter[str] = Counter()
+    for p in all_papers:
+        for c in p.get("categories", [])[:1]:
+            cat_counter[c] += 1
+
+    lines: list[str] = [
+        "# ZED 2i 数据 Pipeline 实时 arXiv 综述（自动生成）",
+        "",
+        f"> **数据来源**：[`research/search_results.json`](search_results.json) 由 [`research/search_info.py`](search_info.py) 通过 HTTP 代理 `127.0.0.1:6984` 拉取自 arxiv.org / api.github.com。",
+        f"> **生成时间**：{meta.get('generated_at', '-')}",
+        f"> **检索代理**：{meta.get('proxy', '-')}",
+        f"> **每主题最多**：{meta.get('max_results_per_topic', '-')} 篇",
+        "",
+        "## 0. 数据概览",
+        "",
+        f"- **arXiv 论文总数**：{total_papers}",
+        f"- **arXiv 主题数**：{len(arxiv)}",
+        f"- **疑似国产团队论文**：{len(china_papers)}（占比 {len(china_papers)*100//max(total_papers,1)}%；🇨🇳 标记，启发式判断）",
+        f"- **GitHub 仓库总数**：{total_repos}",
+        f"- **GitHub 主题数**：{len(github)}",
+        "",
+        "### 0.1 主类目分布（arXiv primary_category）",
+        "",
+    ]
+    for cat, n in cat_counter.most_common(10):
+        lines.append(f"- `{cat}`: {n}")
+    lines.append("")
+
+    lines.extend(
+        [
+            "### 0.2 与本项目框架的映射",
+            "",
+            "| 项目阶段 | 主线主题 | 论文数 |",
+            "|---|---|---|",
+        ]
+    )
+    for topic, m in TOPIC_META.items():
+        n = len(arxiv.get(topic, []))
+        lines.append(f"| {m['stage']} | {m['zh']} | {n} |")
+    lines.append("")
+
+    lines.extend(
+        [
+            "---",
+            "",
+            "# 第一部分 · arXiv 论文（按主题分组，时间新→旧）",
+            "",
+        ]
+    )
+
+    for topic in TOPIC_META.keys():
+        papers = arxiv.get(topic, [])
+        if not papers:
+            continue
+        lines.extend(render_topic(topic, papers))
+        lines.append("---")
+        lines.append("")
+
+    lines.extend(
+        [
+            "# 第二部分 · GitHub 仓库（按 stars 排序）",
+            "",
+        ]
+    )
+    for topic, repos in github.items():
+        lines.extend(render_github_topic(topic, repos))
+
+    lines.extend(
+        [
+            "---",
+            "",
+            "# 第三部分 · 关键洞察与项目对接建议",
+            "",
+            "## I.1 最值得关注的新论文（按相关性挑选）",
+            "",
+            "下方挑选每个主题中**与本项目最相关的 3 篇**（基于标题/摘要语义判断）：",
+            "",
+        ]
+    )
+
+    # 简单挑选每个主题前 3 篇放在洞察区
+    for topic in ["stereo_matching", "visual_inertial_slam", "gaussian_splatting_slam", "monocular_depth_foundation"]:
+        papers = arxiv.get(topic, [])
+        if not papers:
+            continue
+        meta = TOPIC_META[topic]
+        lines.append(f"### {meta['zh']} → {meta['stage']}")
+        for p in sorted(papers, key=lambda x: x.get("published", ""), reverse=True)[:3]:
+            lines.append(f"- **[{p['arxiv_id']}]({p['url']})** {p['title']}（{p['published'][:10]}）")
+        lines.append("")
+
+    lines.extend(
+        [
+            "## I.2 后续动作清单",
+            "",
+            "- [ ] 把上述每主题的 Top-3 论文加入 [`research/zed2i_stereo_vio_arxiv_review.md`](zed2i_stereo_vio_arxiv_review.md) 第 F 节的论文映射表",
+            "- [ ] 对 🇨🇳 标记的论文重点核查机构归属，更新 G 节国产团队清单",
+            "- [ ] 把 GitHub 仓库中 stars > 5k 的项目加入 [`plans/camera/github_opensource_projects.md`](../plans/camera/github_opensource_projects.md)",
+            "- [ ] 每周重跑 [`research/search_info.py`](search_info.py) 增量更新",
+            "",
+            "## I.3 复现方法",
+            "",
+            "```bash",
+            "# 通过 127.0.0.1:6984 代理拉取最新数据",
+            "HTTPS_PROXY=http://127.0.0.1:6984 HTTP_PROXY=http://127.0.0.1:6984 \\",
+            "  python3 research/search_info.py \\",
+            "    --proxy http://127.0.0.1:6984 \\",
+            "    --max-results 10 --delay 5.0 \\",
+            "    --out research/search_results.json",
+            "",
+            "# 渲染为 markdown",
+            "python3 research/gen_review_from_json.py \\",
+            "  --in research/search_results.json \\",
+            "  --out research/zed2i_arxiv_live_review.md",
+            "```",
+            "",
+            "---",
+            "",
+            "**说明**：",
+            "- 本文档由脚本自动生成，可重复执行覆盖",
+            "- 🇨🇳 标记基于作者/摘要中是否包含中国机构关键词的启发式判断，**仅供参考，需人工复核**",
+            "- 摘要截断到 400 字符以控制文档体积",
+            "- 与 [`zed2i_stereo_vio_arxiv_review.md`](zed2i_stereo_vio_arxiv_review.md)（人工综述）互为补充：人工综述给方法论与映射，本文档给最新原始素材",
+        ]
+    )
+
+    with open(args.out, "w", encoding="utf-8") as f:
+        f.write("\n".join(lines))
+
+    print(f"✅ 生成: {args.out}")
+    print(f"   arXiv: {total_papers} 篇，国产疑似: {len(china_papers)}")
+    print(f"   GitHub: {total_repos} 仓库")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())