Search papers, labs, and topics across Lattice.
This paper introduces DigitCode, a novel symbolic tokenization method for hand motion that structures representations by anatomical units, such as bones and fingers, rather than relying solely on continuous parameters like joint angles. By adapting and layering Hand Labanotation's alphabet, DigitCode significantly reduces quantization error by 75% while providing a more interpretable and editable representation of hand motion. The resulting framework not only enhances the accuracy of hand pose generation but also facilitates practical applications in robotics and animation through its training-free, unit-based tokenization approach.
Symbolic tokenization of hand motion reduces quantization error by 75%, enabling precise editing and manipulation of hand poses for robotics and animation.
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.
