LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
[Widzenie komputerowe] Autorzy: Ziqi Ma, Shreya Sharma, Mohamed El Banani i 8 więcej
Camera-controlled video models are rapidly advancing toward long generation horizons and complex camera control. A key failure mode is 3D inconsistency: as the camera moves, objects lose permanence and scene structures shift. Existing post-training techniques, which assign a single scalar reward to the entire generation, are poorly suited to correcting these inconsistencies over long horizons. We introduce LoGo, which blends global and spatially localized rewards for camera-controlled video models. The local reward provides fine-grained credit assignment, which substantially improves 3D consistency, while the global reward preserves camera following and video quality. Across three base models, LoGo shows a clear advantage on DL3DV and TrajectoryBench, a new benchmark for long-horizon, complex-camera-control generation that current evaluations lack. LoGo effectively reduces local object …
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe