AI Paper Atlas

Research map / 3D vision / 3D generation

S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation

Yurui Chen, Junge Zhang, Ziyang Xie, Wenye Li, Feihu Zhang, Jiachen Lu, Li Zhang

TPAMI 2025 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 37 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 pose and vehicle track refinement (ablation)S-NeRF++ · nuScenes 2 scenesPSNR: 28.21 -> 29.09Improved
add optimization-based insertion refinement (ablation)object insertion · WaymoFID: 73.8 -> 62.3Improved
use naive refinement instead of optimization (ablation)object insertion · WaymoFID: 67.1 -> 62.3Mixed
add confidence maps (ablation)S-NeRF++ · nuScenesPSNR: 23.15 -> 24.05Improved
add geometry confidence (ablation)S-NeRF++ · nuScenesPSNR: 23.88 -> 24.05Improved
vary geometry threshold tau (ablation)S-NeRF++ · nuScenesPSNR: 23.93 -> 23.97No clear effect
add view extrapolation with car insertion (ablation)simulation data · nuScenes MV detectionAP: 26.5 -> 33.9Improved
add view interpolation to original views (ablation)simulation data · nuScenes MV detectionAP pretrain: 22.9 -> 23.8No clear effect
add generated foreground assets (ablation)foreground bank · Waymo segmentationmIoU: 58.2 -> 62.8Improved
add reconstructed foreground assets (ablation)foreground bank · nuScenes MV detectionAP: 28.7 -> 33.9Improved
joint training sim and real instead of pretrain then finetune (ablation)DETR3D · nuScenesCar AP: 45.7 -> 39.7Hurt
finetune sim-trained model with 500 realDETR3D · nuScenesCar AP: 33.9 -> 45.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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