变长神经运动拼接：基于簇转移图
Length-varying Neural Motion Stitching via Cluster Transition Graph
浏览论文内容
中文总结 AI 辅助
提出基于簇转移图的变长神经运动拼接方法，通过聚类、路径查找和生成三阶段，自适应过渡长度，生成不同运动间的自然过渡。
中文摘要 AI 辅助
运动拼接旨在通过无缝组合现有运动序列来创建新的角色动画。现有方法通常需要手动选择过渡范围或假设固定的过渡长度，这限制了可连接的运动类型。为了拓宽可合成的运动多样性，生成不同长度的过渡至关重要，这使角色在输入运动差异显著时有足够的时间调整其姿态。为此，我们提出了一种基于簇转移图的变长神经运动拼接方法，该方法在给定两个不同的输入运动时，能生成自然连接的运动序列。我们的框架包含三个阶段：运动聚类、簇路径查找和运动生成。首先，运动聚类将输入运动映射到离散的簇。接着，我们在簇转移图中识别对应的簇，并搜索连接路径。在该图中，节点代表运动簇，有向边表示它们之间的有效过渡。所得路径同时决定过渡长度和指导运动生成的引导序列。最后，将路径和输入运动提供给基于Transformer编码器的运动生成器，以产生最终的过渡姿态。实验结果表明，我们的方法能自适应调整运动长度，并成功地在不同运动（如爬行、篮球投篮和慢速移动）之间生成合理的过渡。我们还表明，与假设固定过渡长度或直接计算时间的方法相比，使用图结构能有效估计过渡持续时间并产生高保真结果。
英文摘要
Motion stitching aims to create new character animations by seamlessly combining existing motion sequences. Existing approaches often require manual selection of transition range or assume fixed transition length, restricting the types of motions that can be connected. To broaden the diversity of motions that can be synthesized, it is essential to generate transitions of varying lengths, allowing the character sufficient time to adapt its pose when the input motions differ significantly. To this end, we propose a length-varying neural motion stitching method based on a cluster transition graph, which produces naturally connected motion sequences given two distinct input motions. Our framework consists of three stages: motion clustering, cluster pathfinding, and motion generation. First, motion clustering maps input motions to discrete clusters. Next, we identify the corresponding clusters in the cluster transition graph and search for a connecting path. In this graph, nodes represent motion clusters, and directed edges indicate valid transitions between them. The resulting path determines both the transition length and a guide sequence that informs motion generation. Finally, the path and input motions are provided to a Transformer encoder-based motion generator to produce the final transition poses. Experimental results demonstrate that our method adaptively adjusts the motion length and successfully generates plausible transitions between distinct motions, such as crawling, basketball shooting, and slow locomotion. We also show that using a graph structure effectively estimates transition durations and produces high-fidelity results compared to methods that assume a fixed transition length, or directly compute the time.
发表机构
- Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。
