AnimaX：運用聯合視頻-姿態擴散模型為無生命物體賦予三維動畫生命

摘要

我們提出AnimaX，這是一種前饋式三維動畫框架，它將視頻擴散模型的運動先驗與基於骨架的動畫可控結構相結合。傳統的運動合成方法要么受限於固定的骨架拓撲結構，要么需要在高維變形空間中進行成本高昂的優化。相比之下，AnimaX有效地將基於視頻的運動知識轉移到三維領域，支持具有任意骨架的多樣化關節網格。我們的方法將三維運動表示為多視角、多幀的二維姿態圖，並實現了基於模板渲染和文本運動提示的聯合視頻-姿態擴散。我們引入了共享的位置編碼和模態感知嵌入，以確保視頻與姿態序列之間的時空對齊，從而有效地將視頻先驗轉移到運動生成任務中。生成的多視角姿態序列通過三角測量轉化為三維關節位置，並通過逆向運動學轉換為網格動畫。在一個新整理的包含160,000個綁定序列的數據集上訓練後，AnimaX在VBench上實現了在泛化性、運動保真度和效率方面的最新成果，為類別無關的三維動畫提供了一個可擴展的解決方案。項目頁面：https://anima-x.github.io/{https://anima-x.github.io/}。

English

We present AnimaX, a feed-forward 3D animation framework that bridges the motion priors of video diffusion models with the controllable structure of skeleton-based animation. Traditional motion synthesis methods are either restricted to fixed skeletal topologies or require costly optimization in high-dimensional deformation spaces. In contrast, AnimaX effectively transfers video-based motion knowledge to the 3D domain, supporting diverse articulated meshes with arbitrary skeletons. Our method represents 3D motion as multi-view, multi-frame 2D pose maps, and enables joint video-pose diffusion conditioned on template renderings and a textual motion prompt. We introduce shared positional encodings and modality-aware embeddings to ensure spatial-temporal alignment between video and pose sequences, effectively transferring video priors to motion generation task. The resulting multi-view pose sequences are triangulated into 3D joint positions and converted into mesh animation via inverse kinematics. Trained on a newly curated dataset of 160,000 rigged sequences, AnimaX achieves state-of-the-art results on VBench in generalization, motion fidelity, and efficiency, offering a scalable solution for category-agnostic 3D animation. Project page: https://anima-x.github.io/{https://anima-x.github.io/}.

AnimaX：運用聯合視頻-姿態擴散模型為無生命物體賦予三維動畫生命

AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models

摘要

Support