BiPO：用于文本到动作合成的双向部分遮挡网络
BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis
AI总结：
BiPO通过整合部分生成与双向自回归架构，提升了文本到动作合成的性能，并在HumanML3D数据集上实现了最先进的结果。
摘要：
从文本描述生成自然且富有表现力的人体动作是一项具有挑战性的任务，因为需要协调完整的身体动态，并在长时间序列中捕捉细微的动作模式，以准确反映给定的文本。为了解决这个问题，我们引入了BiPO，即用于文本到动作合成的双向部分遮挡网络，这是一种新的模型，通过整合基于部分的生成与双向自回归架构来增强文本到动作合成。这种整合使BiPO在生成过程中能够考虑过去和未来的内容，同时在不需真实动作长度的情况下增强对个体身体部分的详细控制。为了缓解由于整合导致的身体部分之间的相互依赖性，我们设计了部分遮挡技术，在训练过程中概率性地遮挡特定动作部分的信息。在我们的全面实验中，BiPO在HumanML3D数据集上实现了最先进的性能，优于最近的方法如ParCo、MoMask和BAMM，在FID分数和整体动作质量方面。值得注意的是，BiPO不仅在文本到动作生成任务中表现出色，还在基于部分生成动作序列和文本描述的动作编辑任务中也表现出色。这些结果揭示了BiPO在推进文本到动作合成方面的有效性及其在实际应用中的潜力。
英文摘要：
Generating natural and expressive human motions from textual descriptions is challenging due to the complexity of coordinating full-body dynamics and capturing nuanced motion patterns over extended sequences that accurately reflect the given text. To address this, we introduce BiPO, Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis, a novel model that enhances text-to-motion synthesis by integrating part-based generation with a bidirectional autoregressive architecture. This integration allows BiPO to consider both past and future contexts during generation while enhancing detailed control over individual body parts without requiring ground-truth motion length. To relax the interdependency among body parts caused by the integration, we devise the Partial Occlusion technique, which probabilistically occludes the certain motion part information during training. In our comprehensive experiments, BiPO achieves state-of-the-art performance on the HumanML3D dataset, outperforming recent methods such as ParCo, MoMask, and BAMM in terms of FID scores and overall motion quality. Notably, BiPO excels not only in the text-to-motion generation task but also in motion editing tasks that synthesize motion based on partially generated motion sequences and textual descriptions. These results reveal the BiPO's effectiveness in advancing text-to-motion synthesis and its potential for practical applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
