发表机构
The University of Hong Kong; Adobe Research（香港大学; 奥多比研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CurveCodec 2提出骨架无关的动画压缩方法，利用学习熵模型编码残差，在保持ACL误差契约下显著减少字节数，并支持跨物种迁移。
AI 中文摘要
骨骼运动以每一帧每个关节的变换形式存储，然而其中大部分信息由身体本身而非运动内容所隐含。压缩是一种在已知身体的情况下询问运动必须额外表达什么的方式，而生产级编解码器必须针对任何骨架在规定的误差界限内回答这一问题。我们之前的编解码器CurveCodec在稀疏锚点上使用学习先验，其平均误差与现代游戏引擎的生产库ACL相当，但在最坏情况下不如ACL，并且其负载以浮点数而非比特计数。在此，我们探究骨骼运动的冗余所在，以及学习模型应接管编解码器的哪一部分。测量结果给出了三个答案。在生产精度下，最大的节省来自根据每个量化曲线的自身历史进行预测；其次是通过层级闭环为每个关节选择哪些样本不进行编码。在编码器留下的间隙上，基于数百万训练样本的最近邻预言机并不优于线性插值，而我们尝试的所有学习型插值器都未能证明其价值。网络真正学习的是编解码器必须发送的残差的分布。CurveCodec 2将每个子轨迹编码为对数映射中的曲线，在闭环中量化并缩减为率失真选择的键，残差通过一个小型学习模型进行熵编码，其整数推理在跨平台上比特精确。每个解码片段都验证了两个契约：ACL自身的最坏情况每关节在规定的容差内，或ACL的每片段平均误差。在来自33个数据集的4,472个片段的保留测试集上，CurveCodec 2在最坏情况契约下，以ACL默认精度0.01厘米，需要ACL字节数的0.37倍；在平均契约下，以0.1厘米精度，需要0.22倍，并在单个CPU核心上解码，且无需重新训练即可迁移到训练中未出现的物种。项目页面：此https URL。
英文摘要
Skeletal motion is stored as every joint's transform at every frame, yet most of it is implied by the body rather than by what the motion is about. Compression is one way to ask what a motion must still say once the body is known, and a production codec must answer it for any skeleton with a stated error bound. Our earlier codec, CurveCodec, matched the mean error of ACL, the production library of modern game engines, with a learned prior over sparse anchors, but not ACL's worst case, and it counted its payload as floats rather than bits. Here we ask where the redundancy of skeletal motion lies and which part of a codec a learned model should take over. Measurements give three answers. At production precision the largest saving comes from predicting each quantized curve from its own past, the second from choosing per joint, in closed loop through the hierarchy, which samples not to code. On the gaps such an encoder leaves, a nearest-neighbour oracle over millions of training samples is no better than linear interpolation, and no learned in-betweener we tried paid for itself. What a network does learn is the distribution of the residuals the codec must send. CurveCodec 2 codes every sub-track as a curve in the log map, quantized in closed loop and thinned to rate-distortion-selected keys, with residuals entropy-coded under a small learned model whose integer inference is bit-exact across platforms. Two contracts are verified on every decoded clip: ACL's own worst case per joint within a stated tolerance, or ACL's mean error per clip. On a held-out test side of 4,472 clips from 33 datasets, CurveCodec 2 needs 0.37x ACL's bytes at ACL's default precision of 0.01 cm under the worst-case contract and 0.22x at 0.1 cm under the mean contract, decodes on one CPU core, and transfers without retraining to a species absent from training. Project page: https://rubbly.cn/publications/curvecodec/
Comments12 pages, 11 figures. Project page: https://rubbly.cn/publications/curvecodec/
