前瞻錨定：在音訊驅動的人體動畫中保持角色身份一致性

摘要

音訊驅動的人體動畫模型在時間自回歸生成過程中常出現身份漂移問題，導致角色隨時間推移逐漸喪失身份特徵。現有解決方案是生成關鍵幀作為中間時間錨點以防止退化，但這需要額外的關鍵幀生成階段，且可能限制自然運動動態。為此，我們提出前瞻錨定技術，該技術利用當前生成窗口前方未來時間步的關鍵幀，而非窗口內的關鍵幀。這使關鍵幀從固定邊界轉變為定向導航標：模型在響應即時音訊線索的同時持續追蹤這些未來錨點，通過持久引導保持身份一致性。該技術還實現了自關鍵幀生成功能，其中參考圖像可直接作為前瞻目標，完全無需關鍵幀生成流程。我們發現前瞻時間距離能自然控制表現力與一致性之間的平衡：較大距離可提供更自由的運動空間，較小距離則強化身份特徵保持。將此技術應用於三種最新人體動畫模型後，前瞻錨定在唇形同步、身份保持和視覺品質方面均實現卓越表現，在多種不同架構中展現出改進的時間調節能力。影片成果請見以下連結：https://lookahead-anchoring.github.io。

English

Audio-driven human animation models often suffer from identity drift during temporal autoregressive generation, where characters gradually lose their identity over time. One solution is to generate keyframes as intermediate temporal anchors that prevent degradation, but this requires an additional keyframe generation stage and can restrict natural motion dynamics. To address this, we propose Lookahead Anchoring, which leverages keyframes from future timesteps ahead of the current generation window, rather than within it. This transforms keyframes from fixed boundaries into directional beacons: the model continuously pursues these future anchors while responding to immediate audio cues, maintaining consistent identity through persistent guidance. This also enables self-keyframing, where the reference image serves as the lookahead target, eliminating the need for keyframe generation entirely. We find that the temporal lookahead distance naturally controls the balance between expressivity and consistency: larger distances allow for greater motion freedom, while smaller ones strengthen identity adherence. When applied to three recent human animation models, Lookahead Anchoring achieves superior lip synchronization, identity preservation, and visual quality, demonstrating improved temporal conditioning across several different architectures. Video results are available at the following link: https://lookahead-anchoring.github.io.

前瞻錨定：在音訊驅動的人體動畫中保持角色身份一致性

Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation

摘要

Support