LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation

Failed to add items

Sorry, we are unable to add the item because your shopping basket is already at capacity.

Add to cart failed.

Please try again later

Add to wishlist failed.

Please try again later

Remove from wishlist failed.

Please try again later

Follow podcast failed

Unfollow podcast failed

LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation

Listen for free

View show details

Camera-controlled video models struggle with 3D inconsistency over long horizons: objects vanish or scene structure shifts as the camera moves. Post-training with a single scalar reward gives poor credit assignment for these local errors. LoGo blends global rewards, which preserve camera following and video quality, with spatially localized rewards that give fine-grained feedback. Tested on three base models, DL3DV, and the new TrajectoryBench for long, complex camera paths, it reduces object shifts, artifacts, and scene changes. 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 Paper: https://arxiv.org/abs/2610.03636v1

No reviews yet