从渐进猜测到固定点：用深度平衡模型重新思考人体运动预测
Progressive Guessing to Fixed Point: Rethinking Human Motion Prediction with Deep Equilibrium Models
将多阶段渐进细化重构为隐式层的固定点问题，用深度平衡模型实现无限次细化但仅需O(1)训练内存，并利用等变几何变换和热启动复用推理计算，为视觉序列预测任务提供高效框架。
原文依据 reformulates progressive guessing paradigm as a fixed point problem within an implicit layer
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期许多人体运动预测方法采用多阶段细化框架，其中每个阶段为下一阶段生成未来姿态的初始猜测。这些猜测通过一系列时空推理阶段逐步向目标预测细化。然而，这种级联设计带来了至少随网络深度线性增长的大量计算和内存开销，并且缺乏明确的停止准则。本文提出MotionDEQ，一种深度平衡运动预测器，将渐进猜测范式重新表述为隐式层内的固定点问题。这种表述在概念上等价于执行无限多次细化步骤，但仅需O(1)的训练内存，并可通过任意黑盒求解器高效求解。我们通过将欧几里得几何变换集成到平衡学习中，精心设计了这一隐式细化过程，使整个网络具有等变性。我们还发现DEQ自然契合运动数据流式到达的现实场景：收敛的固定点可作为热初始猜测复用，从而在后续预测中回收冗余的推理计算。实验表明，MotionDEQ在Human3.6M数据集上以少于300K参数和400ms时55.3mm的预测误差，实现了最优的预测性能和卓越的内存效率。
英文原文摘要 1469 字符
Many recent human motion prediction methods adopt a multi-stage refinement framework, where each stage produces an initial guess of future poses for the next stage. These guesses are progressively refined towards the target prediction through a sequence of spatial-temporal reasoning stages.However, such a cascaded design incurs large computation and memory overheads that grow at least linearly with network depth, and lack an explicit stopping criteria.In this paper, we propose MotionDEQ, a deep equilibrium motion predictor that reformulates progressive guessing paradigm as a fixed point problem within an implicit layer. This formulation is conceptually equivalent to performing infinitely many refinement steps, but requires only O(1) training memory and can be solved efficiently through any black-box solvers. We carefully design this implicit refinement process by integrating Euclidean geometric transformations into equilibrium learning, allowing the entire network to be equivariant. We also find DEQs naturally fit the real-world scenario where motion data comes streamingly: the converged fixed point can be reused as a warm initial guess, to help recycle the redundant inference computation when making subsequent predictions.Our experiments demonstrate that MotionDEQ achieves the state-of-the-art prediction performances with superior memory efficiency, using fewer than 300K parameters with 55.3mm prediction error at 400ms on the Human3.6M dataset.