tweetindex
TR

Ryohei Sasaki@engineer ✓

@rsasaki0109 · japan · joined 12 Jul 2016

Software Engineer at MAP IV(TIER IV group). Previously, Waseda University. AI/Robotics/Autonomous Driving/GNSS/LiDAR/Camera/IMU/SLAM/Localization/Mapping

10 755Followers
299Following
3 191Posts total
108.7KViews on collected posts

Son gönderiler

mevion Low-Cost Open-Source Data Collection System for Powerful and High-Speed Dual-Arm Manipulation https://t.co/pyTzis9Pi8 https://t.co/17KKMwaBIJ
5.4K views · 84 likes · 4 reposts · 1 replies Open on X →
RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval https://t.co/i9rPznR1yE Overview We propose RetrieveVGGT, a training-free streaming 3D reconstruction framework that treats the construction of context for VGGT as a retrieval
3.2K views · 58 likes · 7 reposts · 0 replies Open on X →
[ICML 2026] Trust3R: Trustworthy feed-forward 3D reconstruction with evidential uncertainty. https://t.co/Q2YBrCT5s7 Geometric foundation models such as DUSt3R and MASt3R now predict dense pointmaps from uncalibrated images in a single forward pass. Yet the per-pixel confidence h
4.7K views · 90 likes · 12 reposts · 2 replies Open on X →
VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion (ECCV 2026) https://t.co/8btlc8tkLt VidMap is an offline Structure-from-Motion system for video. It combines temporal tracks, loop closures, metric depth, and global optimization to estimate camera poses,
GIF
8.1K views · 165 likes · 16 reposts · 0 replies Open on X →
modernなGPS測位ライブラリもオープンソースで公開してます! https://t.co/erMb3bAzRL 1.1K views · 5 likes · 0 reposts · 0 replies Open on X →
@rsasaki0109 There was some ancient 2008 paper that was building city models from GNSS line of sight predictions the other way around too: https://t.co/5oN5kgr6pp 574 views · 5 likes · 0 reposts · 1 replies Open on X →
gnss_gpu gnss signal simulator PR https://t.co/ApbUXEZ8an 2.3K views · 29 likes · 2 reposts · 0 replies Open on X →
GPS衛星の電波がGPS受信機に「ちゃんと届くか/ビルに遮られるか」を再現するシミュレーターをオープンソースで作りました! 3D都市モデル上で電波伝搬を計算しています。 リンクはリプにあります! https://t.co/6QB4AyA2Xx
0:10
46K views · 637 likes · 111 reposts · 13 replies Open on X →
RTKLIB v2作った! libgnss++ — Modern C++ GNSS/RTK/PPP Toolkit https://t.co/GcXfkr8ZDg https://t.co/hjR3IAE3EX
37.4K views · 293 likes · 39 reposts · 2 replies Open on X →

Aynı büyüklükteki hesaplara karşı

Son 90 güne ait 4 gönderi, 10K–100K takipçi aralığıyla yan yana. kendi kitlesinin çok ötesine gösteriliyor ve kitle tepki veriyor.

Medyan görüntülenme5 062bu hesap92410K–100K için medyan
Erişim, %47.07%bu hesap3.62%10K–100K için medyan
Etkileşim, %2.14%bu hesap1.52%10K–100K için medyan
ÖlçütBu hesap10K–100K için medyanOran
Gönderi başına medyan görüntülenme5 0629245.48×
Erişim (görüntülenme ÷ takipçi)47.07%3.62%13.0×
Etkileşim oranı2.14%1.52%1.40×

Bu aralıktaki diğer hesaplar →   Başka bir hesapla karşılaştır →   Bu kıyas değerleri nasıl kuruluyor →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

37.4K27 Mar
46K13 Apr
2.3K
574
1.1K15 Apr
8.1K10 Sep
4.7K11 Sep
3.2K12 Sep
5.4K13 Sep

Last 9 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.89%27 Mar
1.66%13 Apr
1.35%
1.05%
0.45%15 Apr
2.23%10 Sep
2.22%11 Sep
2.05%12 Sep
1.64%13 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes56.5%1 366 in total
Reposts7.9%191 in total
Replies0.8%19 in total
Bookmarks34.8%842 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Benzer hesaplar