AI Paper Atlas

Research map / 3D vision / 3D generation

DrivePTS: A Progressive Learning Framework with Textual and Structural Enhancement for Driving Scene Generation

Zhechao Wang, Yiming Zeng, Lufan Ma, Zeqing Fu, Chen Bai, Dongshuo Yin, Ziyao Lin, Cheng Lu

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 0 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 multi-view hierarchical VLM descriptions to the vanilla model (ablation)DrivePTS (T2I-Adapter, SD 2.1) · nuScenes valFID: 15.10 -> 12.03Improved
add multi-view hierarchical descriptions (ablation)DrivePTS · nuScenes valRoad mIoU: 59.77 -> 61.22Improved
add frequency-guided structure loss to the vanilla model (ablation)DrivePTS · nuScenes valRoad mIoU: 59.77 -> 62.92Improved
add frequency-guided structure loss to the vanilla model (ablation)DrivePTS · nuScenes valFID: 15.10 -> 14.47Improved
combine descriptions and frequency loss (ablation)DrivePTS · nuScenes valFID: 12.03 -> 11.68Improved
add mutual information constraint on top of MHD and FGSL (ablation)DrivePTS · nuScenes valVehicle mIoU: 27.16 -> 27.82Improved
add mutual information constraint on top of MHD and FGSL (ablation)DrivePTS · nuScenes valFID: 11.68 -> 11.45Improved
raise lambda_freq from 0 to 0.5 (Stage 1) (ablation)DrivePTS · nuScenes valRoad mIoU: 61.22 -> 63.60Improved
raise lambda_freq to 1 (too large) (ablation)DrivePTS · nuScenes valRoad mIoU: 63.60 -> 61.95Hurt
raise lambda_MI from 0.05 to 0.2 (ablation)DrivePTS · nuScenes valRoad mIoU: 63.95 -> 62.65Hurt
vary alternating iterative step interval in Stage 1 (250 to 3200) (ablation)DrivePTS · nuScenes valRoad/vehicle controllabilityMixed
use DrivePTS synthetic val data to augment BEV segmentation trainingCVT · nuScenes testRoad mIoU: 65.83 -> 67.49Improved

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