arXiv · cs.AI · Mingyi Shi, Huancheng Lin, Taku Komura · 11 小时前模型评分44
CurveCodec 2：面向任意骨架的动画压缩，用学习型熵模型编码残差
CurveCodec 2: Skeleton-agnostic animation compression with a learned entropy model
导读
CurveCodec 2 提出一种不依赖特定骨架的动画压缩编解码器，用小型学习模型对残差做熵编码，整数推理跨平台逐位一致。在 33 个数据集共 4,472 段测试片段上，最坏情况契约下所需字节为 ACL 默认精度 0.01 cm 时的 0.37 倍，平均误差契约下 0.1 cm 时为 0.22 倍，单 CPU 核心即可解码，且无需重训练即可迁移到训练中未出现的物种。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
应用领域：内容与娱乐
事件类型：研究发布
证据摘录
- “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.”
- “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.”
来源：arXiv · cs.AI · arxiv.org