Spatial Context Sensing Research Project

[Spatial Context Sensing Research Project @SCS_Research]

We’re presenting Event-LiDAR at #ECCV2026 this afternoon! Come chat with us about efficient 3D perception by keeping what previous LiDAR scans cannot predict.

🕒 Today, 3:00 PM CEST
📍 ExHall · Poster #12 · Poster Session 6

Looking forward to seeing you there!

[Spatial Context Sensing Research Project @SCS_Research]

🚀 Can we make 3D perception more efficient by processing what changes across LiDAR scans?

We will present Event-LiDAR at #ECCV2026: converting conventional LiDAR scans into sparse 3D events.

Project: https://t.co/IMSozsF83O
Video: https://t.co/cWCbYTcFfs

Details below. 🧵

[Spatial Context Sensing Research Project @SCS_Research]

🚀 Can we make 3D perception more efficient by processing what changes across LiDAR scans?

We will present Event-LiDAR at #ECCV2026: converting conventional LiDAR scans into sparse 3D events.

Project: https://t.co/IMSozsF83O
Video: https://t.co/cWCbYTcFfs

Details below. 🧵

[Ken Sakurada @sakuDken]

村上君（M1）・辻君（D2）の「Event-LiDAR」を #ECCV2026 で発表予定です！

LiDAR点群を3Dイベント化し、認識を効率化します。

📅 9/12 15:00 CEST
📍 ExHall・ポスター #12

#LiDAR #EventCamera #PointCloud #Robotics #AutonomousDriving #PhysicalAI

[Ken Sakurada @sakuDken]

Event-LiDAR: 3D Eventification for Efficient Point Cloud Processing. #ECCV2026

Great work, Masatoshi Murakami & Eisho Tsuji!

📅 Sept 12 · 15:00 CEST
📍 ExHall · Poster #12

#LiDAR #EventCamera #PointCloud #Robotics #AutonomousDriving #PhysicalAI

[Spatial Context Sensing Research Project @SCS_Research]

6/6

Great work by Masatoshi Murakami & Eisho Tsuji, who contributed equally as first authors. Congratulations to both on #ECCV2026!

📅 Sept 12 · 3:00 PM CEST
📍 ExHall · Poster #12 · Poster Session 6

Please stop by our poster.

[Spatial Context Sensing Research Project @SCS_Research]

🚀 Can we make 3D perception more efficient by processing what changes across LiDAR scans?

We will present Event-LiDAR at #ECCV2026: converting conventional LiDAR scans into sparse 3D events.

Project: https://t.co/IMSozsF83O
Video: https://t.co/cWCbYTcFfs

Details below. 🧵

[Spatial Context Sensing Research Project @SCS_Research]

5/6

📊 nuScenes / PTv3, with 1 full scan + 9 eventified scans:

• ~72% fewer input points
• 1.23× faster end-to-end inference
• 63.1 mAP vs. 63.5 for the full-scan baseline

We also demonstrate efficiency gains with CenterPoint.