Research map / Video / Video generation
TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
Mark Yu, Wenbo Hu, Jinbo Xing, Ying Shan
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 Ref-DiT blocks (cross-attention to source video reference tokens) (ablation) | TrajectoryCrafter · iPhone dataset | PSNR: 11.63 -> 14.24 | Improved |
| use Ref-DiT cross-attention instead of directly concatenating source video with point cloud renders (ablation) | TrajectoryCrafter · iPhone dataset | PSNR: 11.05 -> 14.24 | Improved |
| add dynamic monocular training data (double-reprojection on OpenVid-1M) (ablation) | TrajectoryCrafter · iPhone dataset | PSNR: 10.93 -> 14.24 | Improved |
| add static multi-view training data (DL3DV, RealEstate10K) (ablation) | TrajectoryCrafter · iPhone dataset | PSNR: 12.35 -> 14.24 | Improved |
| add static multi-view training data (ablation) | TrajectoryCrafter · iPhone dataset | LPIPS: 0.588 -> 0.519 | Improved |
| TrajectoryCrafter vs best baseline (Shape-of-motion) on mean PSNR | TrajectoryCrafter · iPhone dataset | PSNR: 11.28 -> 14.24 | Improved |
| TrajectoryCrafter vs ViewCrafter on in-the-wild videos | TrajectoryCrafter · In-the-wild videos | VBench Imaging Quality: 0.5548 -> 0.6479 | Improved |
Closest papers by meaning
- ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs (NeurIPS 2025 · similarity 0.87)
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · similarity 0.87)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.87)
- Training-free Camera Control for Video Generation (ICLR 2025 · similarity 0.87)
- SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues (NeurIPS 2026 · similarity 0.87)
- Seurat: From Moving Points to Depth (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.
