📊 2025年との比較
カテゴリ別前年比の詳細
| カテゴリ | 2025年 | 2026年 | 変化 | |:---------|--------:|--------:|-----:| | 🏗️ 3D再構成・SLAM | 119 | 29 | -76% | | 🚗 自動運転 | 32 | 5 | -84% | | 🤖 ロボティクス | 18 | 5 | -72% | | 🧠 VLA・Foundation Model | 13 | 10 | -23% | | 📄 論文紹介 | 14 | 6 | -57% | | 🔧 OSS・ツール | 2 | 4 | +100% | | 💬 その他 | 29 | 16 | -45% |📅 月別カテゴリ推移
月ごとのカテゴリ分布の変化です。
| 月 | 🏗️ | 🚗 | 🤖 | 🧠 | 📄 | 🔧 | 💬 | 計 | 平均♥ |
|---|---|---|---|---|---|---|---|---|---|
| 1月 | 10 | 2 | 3 | 2 | 1 | · | 2 | 20 | 133 |
| 2月 | 8 | · | 1 | 5 | 3 | · | 3 | 20 | 150 |
| 3月 | 11 | 3 | 1 | 3 | 2 | 4 | 11 | 35 | 75 |
🏅 カテゴリ別ベスト
各カテゴリで最もいいねが多かったポストです。
🏆 年間トップ10
1位 💬
♥ 852 / RT 108 / 221,000 views — 2026-02-09
EgoX: Egocentric Video Generation from a Single Exocentric Video
🔗 ポストを見る
2位 🧠
♥ 484 / RT 76 / 21,000 views — 2026-03-10
Describe Anything, Anywhere, at Any Moment DAAAM builds a hierarchical 4D scene graph as spatio-temporal memory, enabling embodied agents to describe anything, anywhere, at any moment.
🔗 ポストを見る
3位 🏗️
♥ 468 / RT 66 / 20,000 views — 2026-02-11
insight-sam3 Uses SAM3 to transfer 2D semantics onto 3D point clouds, producing segmented training data and efficient scene graphs for indoor environments.
🔗 ポストを見る
4位 🧠
♥ 400 / RT 65 / 21,000 views — 2026-01-18
SpatialLLM：Enhancing Large Language Models for Urban Spatial Intelligence SpatialLLM is a comprehensive framework for enhancing Large Language Models with urban spatial understanding capabilities. Thi…
🔗 ポストを見る
5位 📄
♥ 306 / RT 42 / 24,000 views — 2026-02-09
Paper2Rebuttal RebuttalAgent: AI-Powered Academic Paper Rebuttal Assistant RebuttalAgent is an AI-powered multi-agent system that helps researchers craft high-quality rebuttals for academic paper revi…
🔗 ポストを見る
6位 🏗️
♥ 276 / RT 43 / 11,000 views — 2026-01-30
OpenNavMap Structure-Free Topometric Mapping via Large-Scale Collaborative Localization OpenNavMap is a lightweight, structure-free topometric mapping system that enables large-scale collaborative loc…
🔗 ポストを見る
7位 💬
♥ 250 / RT 34 / 15,000 views — 2026-01-22
openvps Open Visual Positioning Service
🔗 ポストを見る
8位 🏗️
♥ 240 / RT 31 / 14,000 views — 2026-03-04
supersplat 3D Gaussian Splat Editor The SuperSplat Editor is a free and open source tool for inspecting, editing, optimizing and publishing 3D Gaussian Splats. It is built on web technologies and runs…
🔗 ポストを見る
9位 🏗️
♥ 235 / RT 36 / 16,000 views — 2026-02-20
[ICLR 2026] FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction FantasyWorld is a unified feed-forward model for joint video and 3D scene generation. The front end emp…
🔗 ポストを見る
10位 🏗️
♥ 227 / RT 33 / 12,000 views — 2026-02-27
Pixie: Physics from Pixels Feed-forward model for predicting 3D physics with 3DGS + NeRF Photorealistic 3D reconstructions (NeRF, Gaussian Splatting) capture geometry & appearance but lack physics. Th…
🔗 ポストを見る