AI 中文总结
本文提出DigitCode，沿手部解剖单元层次结构调整HL字母表以构建离散符号表征，将量化误差降低四分之三，发布HandTok测试平台，可用于修复生成的畸形手部及机器人重定向等任务。
AI 中文摘要
手部运动承载着人类活动中最精细粒度的信息，但用于手部生成、理解及机器人学习的表征大多是连续的——如关节角或MANO参数。这些表征虽准确，但缺乏结构性：手指无法作为符号被索引或编辑，也没有标记姿势是否符合解剖学有效性。离散符号表征恰好提供了这种结构，手部拉班记谱法（Hand Labanotation, HL）已证明其对手部可行，将运动写为T×40的网格，每块骨骼对应一个固定方向符号。基于该网格，本文探究符号应跨越的解剖单元：骨骼、手指或整只手。DigitCode通过在一个编码内沿手部单元层次结构调整、分组和分层HL字母表来回答该问题，使符号表征的量化误差降低四分之三。关键在于单元而非量化器类型：在固定单元下，无需训练的量化器与学习得到的强量化器在重构上可互换，而沿解剖层次下移才会改变精度。该层次结构还能适配下游任务需求。由于手指是真实可枚举单元，每个手指令牌可作为无需训练的可编辑工具，用于解决连续表征无法处理的任务——修复生成的畸形手部，以及将其重定向到机器人。本文发布了可复现的测试平台HandTok，以便对不同手部分词器进行单元间比较。项目页面：this https URL。
英文摘要
Hand motion carries the finest-grained information in human activity, yet the representations behind hand generation, understanding, and robot learning are overwhelmingly continuous--joint angles or MANO parameters. These are accurate but unstructured: a finger cannot be indexed or edited as a symbol, and nothing marks a pose as anatomically valid. Discrete symbolic representations supply exactly this structure, and Hand Labanotation (HL) has shown they are feasible for the hand, writing motion as a T x 40 grid of one fixed direction symbol per bone. Building on this grid, we ask the question underneath it: the anatomical unit a symbol should span--bone, finger, or whole hand. DigitCode answers it by adapting, grouping, and layering HL's alphabet along the hand's unit hierarchy within one code, cutting the symbolic representation's quantization error by three quarters. The lever is the unit, not the quantizer family: at a fixed unit, training-free and learned strong quantizers are interchangeable on reconstruction, while moving down the anatomical hierarchy is what shifts accuracy. The hierarchy also tracks what downstream tasks need. Because a finger is a genuine, enumerable unit, one per-finger token doubles as a training-free, editable handle for jobs a continuous representation cannot address--repairing malformed generated hands, and retargeting them onto robots. We release HandTok, a reproducible testbed, so hand tokenizers can be compared unit-for-unit. Project page: https://digitcode-demo.github.io.
