AI Paper Atlas

Research map / 3D vision / 3D generation

UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

Yuping Wang, Xiangyu Huang, Xiaokang Sun, Mingxuan Yan, Shuo Xing, Zhengzhong Tu, Jiachen Li

ICCV 2025 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 20 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
add voxel-level flow input and flow decoderOccWorld · nuScenes forecastingmIoU_geo at 0s: 66.79 -> 70.64Improved
add voxel-level flow input and flow decoderOccWorld · nuScenes forecastingIoU_bg: 53.27 -> 59.56Improved
add voxel-level flow input and flow decoderOccWorld · Waymo forecastingmIoU_geo at 0s: 68.24 -> 71.35Improved
use object-level flow instead of noneOccWorld · nuScenes forecastingmIoU_geo at 0s: 66.79 -> 65.41No clear effect
use object-level flow instead of noneOccWorld · Waymo forecastingIoU_bg: 56.06 -> 55.56No clear effect
train on Waymo instead of nuScenes, test on nuScenesOccWorld · nuScenes forecastingmIoU_geo at 0s: 70.64 -> 63.22Hurt
add Waymo to nuScenes training dataOccWorld · nuScenes forecastingmIoU_geo at 3s: 19.06 -> 20.15Improved
add CARLA to nuScenes training dataOccWorld · nuScenes forecastingIoU_bg: 59.56 -> 55.07Hurt
add CARLA to nuScenes training dataOccWorld · nuScenes forecastingP_car: 82.57 -> 82.97No clear effect
add CARLA to Waymo training dataOccWorld · Waymo forecastingIoU_geo at 1s: 36.04 -> 42.54Improved
use highway-only CARLA instead of full-speed CARLA when mixing with nuScenes (ablation)OccWorld · nuScenes forecastingIoU_bg: 55.07 -> 61.40Improved
use highway-only CARLA instead of full-speed CARLA when mixing with nuScenes (ablation)OccWorld · nuScenes forecastingIoU_car: 77.87 -> 85.59Improved

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