AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Streaming Object Detection for 3-D Point Clouds

Wei Han, Zhengdong Zhang, Benjamin Caine, Brandon Yang, Christoph Sprunk, Ouais Alsharif, Jiquan Ngiam, Vijay Vasudevan, Jonathon Shlens, Zhifeng Chen

ECCV 2020 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 33 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
restrict the detector to a single slice (localized receptive field)Non-streaming baseline · Waymo vehicles, 16 slicesmAP: 51.0 -> 35.0Hurt
increase slices from 16 to 32 without stateLocalized receptive field · Waymo vehiclesmAP: 35.0 -> 10.5Hurt
add global NMS over all slices (ablation)Localized receptive field · Waymo vehicles, 32 slicesmAP: 10.5 -> 39.2Improved
add stateful NMS (k=1)Localized receptive field · Waymo vehicles, 32 slicesmAP: 10.5 -> 39.0Improved
use stateful NMS instead of global NMS (ablation)Global NMS · Waymo pedestrians, 16 slicesmAP: 54.8 -> 54.9No clear effect
add LSTM recurrence to stateful NMSStreaming PointPillars · Waymo vehicles, 32 slicesmAP: 39.2 -> 48.9Improved
add LSTM recurrence to stateful NMSStreaming detector · Waymo vehicles, objects subtending 0-5 degmAP: 9.0 -> 10.8Improved
add stateful NMSLocalized RF · Waymo vehicles, objects subtending >35 degmAP: 14.0 -> 68.0Improved
stream with 8 slices, stateful NMS and RNN, instead of full rotationNon-streaming baseline · Waymo vehicles (PointPillars)latency (ms): 116 -> 17Improved
scale up streaming model (larger grid) vs non-streaming baselinePointPillars pedestrians · Waymo pedestriansmAP: 54.9 -> 60.1Improved

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