AI Paper Atlas

Research map / Video / Video generation

ConsistentCity: Semantic Flow-guided Occupancy DiT for Temporally Consistent Driving Scene Synthesis

Benjin Zhu, Xiaogang Wang, Hongsheng Li

ICCV 2025 · Video › Video generation · approach: World-model video generation · 1 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 flow-guided feature warping (ablation)SF-DiT baseline · nuScenes video synthesisFID: 15.4 -> 11.2Improved
add semantic flow-guided feature warping (ablation)SF-DiT baseline · nuScenes video synthesisFVD: 94.2 -> 81.3Improved
add adaptive attention modulation (ablation)SF-DiT with feature warping · nuScenes video synthesisFID: 11.2 -> 9.4Improved
add FlowResEstimator (ablation)SF-DiT with attention modulation · nuScenes video synthesisFID: 9.4 -> 8.9Improved
add flow uncertainty (ablation)SF-DiT with FlowResEstimator · nuScenes video synthesisFID: 8.9 -> 8.5Improved
add flow classification (ablation)SF-DiT with uncertainty · nuScenes video synthesisFID: 8.5 -> 8.3Improved
use SFMCA instead of spatial-temporal self-attention (ablation)SF-DiT · nuScenes video synthesisFVD: 235.1 -> 73.6Improved
use SFMCA instead of spatial self + temporal cross attention (ablation)SF-DiT · nuScenes video synthesisFVD: 94.2 -> 73.6Improved
add depth to semantics conditioning (ablation)ControlNet with SFMCA · nuScenes video synthesisFID: 12.8 -> 9.1Improved
add flow to depth conditioning (ablation)ControlNet with SFMCA · nuScenes video synthesisFID: 13.9 -> 11.4Improved
add flow to semantics+depth conditioning (ablation)ControlNet with SFMCA · nuScenes video synthesisFID: 9.1 -> 8.3Improved
increase sequence length from 4 to 8 frames (ablation)SF-DiT · nuScenes video synthesisFID: 10.2 -> 8.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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