AI Paper Atlas

Research map / Video / Video generation

InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation

Zhuoran Yang, Xi Guo, Chenjing Ding, Chiyu Wang, Wei Wu, Yanyong Zhang

ICCV 2025 · Video › Video generation · approach: World-model video generation · 6 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 Instance Flow Guider (ablation)InstaDrive · nuScenes val (T+I)2VFVD: 58.86 -> 38.06Improved
add Instance Flow Guider (ablation)InstaDrive · nuScenes val (T+I)2VIDS: 1189 -> 532Improved
add Instance Flow Guider (ablation)InstaDrive · nuScenes val (T+I)2VFID: 6.28 -> 3.96Improved
add Instance Flow Guider (ablation)InstaDrive · nuScenes val (T+I)2VNDS: 40.23 -> 40.51No clear effect
add Spatial Geometric Aligner (ablation)InstaDrive · nuScenes val (T+I)2VNDS: 37.31 -> 40.51Improved
add Spatial Geometric Aligner (ablation)InstaDrive · nuScenes val (T+I)2VIDS: 723 -> 532Improved
add Spatial Geometric Aligner (ablation)InstaDrive · nuScenes val (T+I)2VFVD: 41.21 -> 38.06Improved
use box projection instead of box coordinates as control (ablation)InstaDrive · nuScenes val (T+I)2VNDS: 38.22 -> 40.51Improved
add depth-order cues (ablation)InstaDrive · nuScenes val (T+I)2VNDS: 39.13 -> 40.51Improved
add generated data to real data when training StreamPETRStreamPETR · nuScenes detectionNDS: 48.3 -> 51.9Improved
add generated data to real data when training StreamPETRStreamPETR · nuScenes detectionmAP: 38.3 -> 42.0Improved
add InstaDrive generated data to real data for trackingStreamPETR · nuScenes MOTIDS: 687 -> 532Improved

Later papers that compared with this method

1 later accepted paper reports InstaDrive as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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