Research map / Video / Video generation
Who Does What and Where to Go: Orthogonal Alignment and Hierarchical Planning for Multi-Entity Trajectories
Zhang Wan, Yu Li, Tianze Huang, Juan Cao, Sheng Tang
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 Geometry-Aware BEV prior (ablation) | ProgTraj-Director · Stepwise-ME | CR: 19.8 -> 7.3 | Improved |
| add Geometry-Aware BEV prior (ablation) | ProgTraj-Director · Stepwise-ME | FID: 54.21 -> 43.65 | Improved |
| add Geometry-Aware BEV prior (ablation) | ProgTraj-Director · Stepwise-ME | F1: 0.862 -> 0.875 | Improved |
| add Action Prior (ablation) | ProgTraj-Director · Stepwise-ME | Acc.: 0.68 -> 0.96 | Improved |
| add Action Prior (ablation) | ProgTraj-Director · Stepwise-ME | F1: 0.743 -> 0.875 | Improved |
| add Action Prior (ablation) | ProgTraj-Director · Stepwise-ME | CR: 11.2 -> 7.3 | Improved |
| add Identity Lineage (ablation) | ProgTraj-Director · Stepwise-ME | F1: 0.718 -> 0.875 | Improved |
| add Identity Lineage (ablation) | ProgTraj-Director · Stepwise-ME | FID: 58.74 -> 43.65 | Improved |
| add Identity Lineage (ablation) | ProgTraj-Director · Stepwise-ME | Acc.: 0.82 -> 0.96 | Improved |
| add all three components to vanilla diffusion (ablation) | ProgTraj-Director · Stepwise-ME | CR: 40.7 -> 7.3 | Improved |
| ProgTraj-Director vs Lang2Motion | ProgTraj-Director · Stepwise-ME | CR: 16.4 -> 7.3 | Improved |
| ProgTraj-Director vs GenDoP on single-entity data | ProgTraj-Director · DataDop | F1: 0.414 -> 0.416 | No clear effect |
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.
- GenDoP — GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography (ICCV 2025) · better on 6 of 6 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
- Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding (ECCV 2026 · similarity 0.88)
- Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories (ECCV 2026 · similarity 0.87)
- Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation (ICML 2026 · similarity 0.86)
- Unveiling the Value of Motion for Cinematic Camera Trajectories (NeurIPS 2026 · similarity 0.86)
- ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation (CVPR 2026 · similarity 0.86)
- RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation (CVPR 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.
