cs.CVNov 2, 2026

Fast-Slow Evolutionary Occupancy Prediction via Controlled Dynamics

Authors: Runhe Yang, Zhiyuan Zhou, Yuxiang Yan, Xuetong Yang, Yikai Pan, Jiacheng Tang, Zhuolin He, Jianhua Han, 

Organizations: Fudan University · Yinwang Intelligent Technology

Abstract

3D semantic occupancy prediction provides dense geometric and semantic scene representations for autonomous driving, where both high accuracy and low response latency are crucial for safe downstream forecasting and planning. Existing methods usually exhibit different accuracy-latency characteristics. Performance-oriented models provide stronger geometric and semantic predictions, while deployment-friendly models provide faster responses. This motivates EvoOcc, a fast-slow evolutionary occupancy prediction framework that jointly exploits their complementary strengths to improve the accuracy-latency balance without changing the upstream architectures. EvoOcc models evolutionary occupancy prediction as a continuous time controlled dynamical system, enabling flexible adaptation to variable slow system delays and irregular fast system arrivals. The framework further decomposes the evolution process into dual state evolution where ego state evolution compensates for the deterministic coordinate shifts and scene state evolution models the genuine geometric and semantic scene changes. Extensive experiments on three different fast-slow system pairs and irregular prediction arrivals show that EvoOcc consistently improves over fast system baselines while maintaining much lower latency than the slow system, indicating a favorable accuracy-latency balance and stable behavior under practical inference situations.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SparseOcc++: Geometry-Aware Sparse Latent Representation for Semantic Occupancy Prediction

    Jul 6, 2026Pin Tang, Zhongdao Wang, Guoqing Wang +23D ReconstructionAutonomous Driving Perception

  2. GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning

    May 17, 2026Cheng Chen, Hao Huang, Saurabh Bagchi3D Gaussian SplattingWorld Model Learning

  3. OPUS-V2: Bridging the Gap between Sparse Points and Dense Voxels

    Aug 29, 2026Jiabao Wang, Qiang Meng, Liujiang Yan +33D Occupancy PredictionAutonomous Driving