AI Paper Atlas

Research map / Point clouds / Point cloud classification

DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving

Chen Shi, Shaoshuai Shi, Kehua Sheng, Bo Zhang, Li Jiang

ICCV 2025 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 14 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 semantic supervision to depth supervision (ablation)DriveX-S world encoder · FlowOcc3D occupancy and flowmIoU: 3.96 -> 42.53Improved
add color reconstruction supervision (ablation)DriveX-S world encoder · FlowOcc3D occupancy and flowmIoU: 42.53 -> 43.47Improved
add future prediction (2 frames) in FSA (ablation)DriveX-S with ViewFormer · FlowOcc3D occupancy and flowmAVE: 0.415 -> 0.385Improved
extend prediction horizon from 2 to 4 frames (ablation)DriveX-S with ViewFormer · FlowOcc3D occupancy and flowmIoU: 43.47 -> 43.59No clear effect
use decoupled instead of joint training (ablation)DriveX · nuScenes point cloud forecastingavg Chamfer Distance (m^2): 1.41 -> 1.06Improved
add dynamic-aware ray sampling (ablation)DriveX decoupled · nuScenes point cloud forecastingavg Chamfer Distance (m^2): 1.06 -> 1.02Improved
use direct instead of autoregressive future prediction (ablation)DriveX · nuScenes point cloud forecastingavg Chamfer Distance (m^2): 1.32 -> 1.02Improved
scale training data from 50% to 100% (ablation)DriveX · nuScenes point cloud forecastingavg Chamfer Distance (m^2): 1.53 -> 1.02Improved
scale training data from 10% to 50% (ablation)DriveX · nuScenes point cloud forecastingavg Chamfer Distance (m^2): 2.30 -> 1.53Improved
add DriveX-S features to ViewFormerViewFormer · FlowOcc3D occupancy (no flow head)mIoU: 43.61 -> 44.38Improved
add ViDAR pretraining to ViewFormerViewFormer · FlowOcc3D occupancy (no flow head)mIoU: 43.61 -> 43.72No clear effect
add DriveX-S to DiffusionDrive-CDiffusionDrive-C · NAVSIM testPDMS: 83.6 -> 84.5Improved

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