AI Paper Atlas

Research map / 3D vision / 3D generation

Fast-Slow Evolutionary Occupancy Prediction via Controlled Dynamics

Runhe Yang, Zhiyuan Zhou, Yuxiang Yan, Xuetong Yang, Yikai Pan, Jiacheng Tang, Zhuolin He, Jianhua Han, Hang Xu, Jian Pu

NeurIPS 2026 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a fast-slow evolutionary framework for 3D semantic occupancy prediction from driving sensors that aims to combine high accuracy with low latency.

Problem

3D semantic occupancy prediction for autonomous driving faces a trade-off: performance-oriented models are accurate but slow, while deployment-friendly models are fast but less accurate.

Approach

Uses a fast-slow evolutionary scheme with controlled dynamics to get accuracy and low latency together; details are not available from the abstract alone.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace control increment with elapsed time (ablation)EvoOcc · Ablation streaming (ALOcc-2D-mini / ALOcc-3D)mIoU / RayIoU: 40.3 -> 39.9 mIoU; 41.5 -> 41.1 RayIoUHurt
add ray-termination loss (ablation)EvoOcc · Ablation streaming (ALOcc-2D-mini / ALOcc-3D)RayIoU: 40.4 -> 41.5Improved
add ray-termination loss (ablation)EvoOcc · Ablation streaming (ALOcc-2D-mini / ALOcc-3D)mIoU: 40.6 -> 40.3No clear effect
add ray-termination loss (ablation)EvoOcc · Surface-geometry diagnosticsextra occupancy (%): 4.30 -> 3.01Improved
use scene state evolution instead of convolution learned fusion (ablation)EvoOcc · Ablation streaming (ALOcc-2D-mini / ALOcc-3D)mIoU: 39.8 -> 40.3Improved
use scene state evolution instead of attention learned fusion (ablation)EvoOcc · Ablation streaming (ALOcc-2D-mini / ALOcc-3D)mIoU: 38.4 -> 40.3Improved
add EvoOcc evolution to fast systemALOcc-2D-mini / ALOcc-3D · Occ3D-nuScenes val offlinemIoU: 33.4 -> 39.3Improved
ego-motion warping only of delayed slow (no scene evolution) (ablation)delayed slow system · Occ3D-nuScenes val offlinemIoU_D: 31.3 -> 20.0 (vs fast, ALOcc pair)Hurt
add EvoOcc in streaming settingfast systems · Occ3D-nuScenes val streamingmIoU: +4.3 to +6.9Improved
lengthen slow system invocation interval 0.5 s to 5.0 sEvoOcc · ALOcc pair streamingmIoU: 40.3 -> 38.9; 23.6 -> 11.0 TFLOPs/sceneMixed
lengthen slow invocation interval to 20.0 sEvoOcc · ALOcc pair streamingmIoU: 40.3 -> 35.6Mixed
vary fast arrival rate (fixed, alternating, random)EvoOcc · irregular arrivalmIoU_D / RayIoU: mIoU_D varies at most 0.2; RayIoU at most 0.1No clear effect

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