LoGo：面向一致长时程视频生成的局部-全局奖励方法

Authors:Ziqi Ma, Shreya Sharma, Mohamed El Banani, Katja Schwarz, Chongjie Ye, Chao-Yuan Wu, Li Fei-Fei, Ben Mildenhall, Georgia Gkioxari, Justin Johnson, Gowthami Somepalli

View PDF HTML (experimental)

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: this https URL

Comments:	Project website: this https URL
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.03636 [cs.CV]
	(or arXiv:2610.03636v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2610.03636 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ziqi Ma [view email]
[v1] Fri, 2 Oct 2026 17:26:18 UTC (3,836 KB)