Abstract
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 shifts, artifacts, and global scene changes, illustrating the importance of credit assignment in post-training video models. Project website: https://ziqi-ma.github.io/logo-website/
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ma, Z., Sharma, S., El Banani, M., Schwarz, K., Ye, C., Wu, C. Y., Fei-Fei, L., Mildenhall, B., Gkioxari, G., Johnson, J., & Somepalli, G. (2026). LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation. https://omanscience.com/en/articles/logo-local-global-rewards-for-consistent-long-horizon-video-generation
MLA 9
Ma, Ziqi, et al. "LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation." https://omanscience.com/en/articles/logo-local-global-rewards-for-consistent-long-horizon-video-generation.
Chicago (author–date)
Ma, Ziqi, Shreya Sharma, Mohamed El Banani, Katja Schwarz, Chongjie Ye, Chao-Yuan Wu, Li Fei-Fei, Ben Mildenhall, Georgia Gkioxari, Justin Johnson, and Gowthami Somepalli. 2026. "LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation." https://omanscience.com/en/articles/logo-local-global-rewards-for-consistent-long-horizon-video-generation.
Harvard
Ma, Z., Sharma, S., El Banani, M., Schwarz, K., Ye, C., Wu, C. Y., Fei-Fei, L., Mildenhall, B., Gkioxari, G., Johnson, J. and Somepalli, G. (2026) 'LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation', Available at: https://omanscience.com/en/articles/logo-local-global-rewards-for-consistent-long-horizon-video-generation.
Vancouver
Ma Z, Sharma S, El Banani M, Schwarz K, Ye C, Wu CY, et al. LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation. https://omanscience.com/en/articles/logo-local-global-rewards-for-consistent-long-horizon-video-generation
IEEE
Z. Ma, S. Sharma, M. El Banani, K. Schwarz, C. Ye, C. Y. Wu, L. Fei-Fei, B. Mildenhall, G. Gkioxari, J. Johnson, and G. Somepalli, "LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation," https://omanscience.com/en/articles/logo-local-global-rewards-for-consistent-long-horizon-video-generation.