Research map / 3D vision / 3D generation
READ: Large-Scale Neural Scene Rendering for Autonomous Driving
Zhuopeng Li, Lu Li, Jianke Zhu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use READ instead of the strongest listed baseline | Novel-view rendering on KITTI and Brno Urban · KITTI Residential, Road, and City; Brno Urban total; both reported test protocols | PSNR: 17.70 vs 15.70; 20.26 vs 17.63; 18.35 vs 15.67; 22.09 vs 19.07; 24.29 vs 20.25; 23.48 vs 20.08; 16.56 vs 15.54; 21.69 vs | Improved |
| Add the basic gate module to sampling NPBG (ablation) | Sampling NPBG · KITTI Road | PSNR: 20.63 -> 22.29 | Improved |
| Add same-scale feature fusion (ablation) | READ with Gate · KITTI Road | PSNR: 22.29 -> 23.76 | Improved |
| Add different-scale feature fusion (ablation) | READ with Gate and Same · KITTI Road | PSNR: 23.76 -> 24.29 | Improved |
| Add L1 and PSNR losses to VGG loss (ablation) | READ with Gate, Same, and Differ · KITTI Road | SSIM: 0.7402 -> 0.7490 | Improved |
| Add L1 loss to VGG loss (ablation) | READ with Gate, Same, and Differ · KITTI Road | PSNR: 24.29 -> 24.16 | Hurt |
| Add PSNR loss to VGG loss (ablation) | READ with Gate, Same, and Differ · KITTI Road | PSNR: 24.29 -> 23.96 | Hurt |
| Stitch scenes | READ · KITTI | PSNR: 22.08 -> 22.58 | Improved |
Closest papers by meaning
- Multi-Level Neural Scene Graphs for Dynamic Urban Environments (CVPR 2024 · similarity 0.87)
- ViiNeuS: Volumetric Initialization for Implicit Neural Surface Reconstruction of Urban Scenes with Limited Image Overlap (CVPR 2025 · similarity 0.87)
- SceneCrafter: Controllable Multi-View Driving Scene Editing (CVPR 2025 · similarity 0.87)
- DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving (NeurIPS 2025 · similarity 0.87)
- X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability (NeurIPS 2025 · similarity 0.87)
- StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models (CVPR 2025 · similarity 0.87)
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.
