DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
| Autor: | Cho, Jungbin, Kim, Junwan, Kim, Jisoo, Kim, Minseo, Kang, Mingu, Hong, Sungeun, Oh, Tae-Hyun, Yu, Youngjae |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Human motion, inherently continuous and dynamic, presents significant challenges for generative models. Despite their dominance, discrete quantization methods, such as VQ-VAEs, suffer from inherent limitations, including restricted expressiveness and frame-wise noise artifacts. Continuous approaches, while producing smoother and more natural motions, often falter due to high-dimensional complexity and limited training data. To resolve this "discord" between discrete and continuous representations, we introduce DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding, a novel method that decodes discrete motion tokens into continuous motion through rectified flow. By employing an iterative refinement process in the continuous space, DisCoRD captures fine-grained dynamics and ensures smoother and more natural motions. Compatible with any discrete-based framework, our method enhances naturalness without compromising faithfulness to the conditioning signals. Extensive evaluations demonstrate that DisCoRD achieves state-of-the-art performance, with FID of 0.032 on HumanML3D and 0.169 on KIT-ML. These results solidify DisCoRD as a robust solution for bridging the divide between discrete efficiency and continuous realism. Our project page is available at: https://whwjdqls.github.io/discord.github.io/. Comment: 20 pages 18 figures |
| Databáze: | arXiv |
| Externí odkaz: |
|