MemoBench：在動態變化環境中進行世界建模的基準測試

摘要

影片生成模型旨在模擬動態環境，目前已有數個基準測驗用於評估跨幀的記憶一致性。然而，多數基準僅在目標對象仍處於視野範圍內時評估一致性，少數迫使物體離開視野的測試，也僅針對遮擋期間無任何變化的靜態場景。為填補此缺口，我們提出 MemoBench，這是一個基於「消失與再現」典範的診斷基準，應用於動態變化的環境中：目標物體經歷物理過程，從視野中消失，並必須在重新出現時，準確恢復其更新後的狀態。我們收集了 360 個真實片段，涵蓋合成與真實世界場景，並設計一套評估套件，結合自動化指標與基於視覺問答的評估，涵蓋四大診斷支柱。針對八個最先進模型的評估結果，揭示了在「消失與再現」典範下，關於記憶一致性的關鍵洞見與未解挑戰。

English

Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency only while the target remains in view, and the few that force objects out of view evaluate static scenes where nothing changes during occlusion. To bridge this gap, we introduce MemoBench, a diagnostic benchmark built around the disappear-and-reappear paradigm in dynamically changing environments: a target object undergoes a physical process, disappears from view, and must be correctly recovered in its updated state upon reappearance. We curate 360 ground-truth clips spanning synthetic and real-world scenes, and design an evaluation suite combining automated metrics with VQA-based assessment across four diagnostic pillars. Evaluation of eight state-of-the-art models reveals key insights and open challenges regarding memory consistency under the disappear-and-reappear paradigm.