Research map / 3D vision / 3D generation
ReCamDriving: LiDAR-Free Camera-Controlled Video Synthesis for Novel Trajectories
Yaokun li, Shuaixian Wang, Mantang GUO, Jiehui Huang, Taojun Ding, Mu Hu, Kaixuan Wang, Shaojie Shen, Guang Tan
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 |
|---|---|---|---|
| add 3DGS rendering condition (Stage 2) on top of pose-only control (ablation) | ReCamDriving · WOD (camera-condition ablation) | FID: 34.86 -> 24.88 | Improved |
| add 3DGS rendering condition (Stage 2) on top of pose-only control (ablation) | ReCamDriving · WOD (camera-condition ablation) | Translation error: 4.23 -> 2.55 | Improved |
| use 3DGS renderings instead of LiDAR projection as Stage 2 condition (ablation) | ReCamDriving · WOD (camera-condition ablation) | FVD: 27.78 -> 19.18 | Improved |
| use 3DGS renderings instead of LiDAR projection as Stage 2 condition (ablation) | ReCamDriving · WOD (camera-condition ablation) | Translation error: 2.69 -> 2.55 | Improved |
| add LiDAR projection on top of 3DGS renderings (ablation) | ReCamDriving · WOD (camera-condition ablation) | FID: 24.88 -> 24.75 | No clear effect |
| add LiDAR projection on top of 3DGS renderings (ablation) | ReCamDriving · WOD (camera-condition ablation) | IQ: 63.63 -> 63.42 | No clear effect |
| use camera-controlled generation instead of repair-style generation (ablation) | ReCamDriving · WOD (repair baseline comparison) | FID: 40.87 -> 24.88 | Improved |
| use camera-controlled generation instead of repair-style generation (ablation) | ReCamDriving · WOD (repair baseline comparison) | CLIP-V: 91.32 -> 96.64 | Improved |
| use two-stage progressive training instead of single-stage joint training (ablation) | ReCamDriving · WOD and NuScenes (training strategy ablation) | FVD: 25.16 -> 18.32 | Improved |
| use two-stage progressive training instead of single-stage joint training (ablation) | ReCamDriving · WOD and NuScenes (training strategy ablation) | IQ: 59.97 -> 63.42 | Improved |
| use lateral cross-trajectory pairs instead of longitudinal splits (ablation) | ReCamDriving · WOD (data curation ablation) | Rotation error: 1.97 -> 1.49 | Improved |
| use lateral cross-trajectory pairs instead of longitudinal splits (ablation) | ReCamDriving · WOD (data curation ablation) | FVD: 28.54 -> 19.18 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FreeVS — FreeVS: Generative View Synthesis on Free Driving Trajectory (ICLR 2025) · better on 2 of 2 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
- SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues (NeurIPS 2026 · similarity 0.87)
- Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis (NeurIPS 2026 · similarity 0.87)
- AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers (CVPR 2025 · similarity 0.86)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.86)
- SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving (CVPR 2025 · similarity 0.86)
- Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency (NeurIPS 2025 · similarity 0.86)
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.
