AI Paper Atlas

Research map / Point clouds / Segmentation and detection

ESAM++: Efficient Online 3D Perception on the Edge

Qin Liu, Lavisha Aggarwal, Saptarashmi Bandyopadhyay, Vikas Bahirwani, Marc Niethammer, Ehsan Adeli, Andrea Colaco

CVPR 2026 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use SFPN-Small instead of MinkNet18 backboneESAM++ · ScanNet200 CPUmAP: 27.1 -> 30.3Improved
use SFPN-Small instead of MinkNet18 backboneESAM++ · ScanNet200 CPUCPU latency (ms): 487ms -> 211msImproved
use SFPN-Small instead of SPVNASESAM++ · ScanNet200 CPUmAP: 22.8 -> 30.3Improved
use SFPN-Large instead of ESAM-E Sparse UNetESAM++ · ScanNet200 CPUCPU latency (ms): 934ms -> 326msImproved
use SFPN-Large instead of ESAM-E Sparse UNetESAM++ · ScanNet200mAP: 43.4 -> 43.7No clear effect
scale backbone from SFPN-Small to SFPN-Base (ablation)ESAM++ · ScanNet200mAP: 30.3 -> 39.7Improved
scale backbone from SFPN-Base to SFPN-Large (ablation)ESAM++ · ScanNet200mAP: 39.7 -> 43.7Improved
train with 100% instead of 50% of the data (ablation)ESAM++ · ScanNet200 class-agnosticAP: 40.6 -> 43.7Improved
train with 50% instead of 10% of the data (ablation)ESAM++ · ScanNet200 class-agnosticAP: 32.4 -> 40.6Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy