LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
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 generatio...
Ziqi Ma, Shreya Sharma, Mohamed El Banani et al.
· 0 citations