FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing
This work addresses the need for more detailed motion generation and editing in computer vision and animation, though it is incremental as it builds on existing text-to-motion methods by adding richer annotations.
The authors tackled the problem of generating realistic human motions from text by addressing the lack of specific body part and timing details, resulting in a new dataset (FineMotion) that improved Top-3 accuracy by +15.3% for the MDM model and enabled zero-shot fine-grained motion editing.
Generating realistic human motions from textual descriptions has undergone significant advancements. However, existing methods often overlook specific body part movements and their timing. In this paper, we address this issue by enriching the textual description with more details. Specifically, we propose the FineMotion dataset, which contains over 442,000 human motion snippets - short segments of human motion sequences - and their corresponding detailed descriptions of human body part movements. Additionally, the dataset includes about 95k detailed paragraphs describing the movements of human body parts of entire motion sequences. Experimental results demonstrate the significance of our dataset on the text-driven finegrained human motion generation task, especially with a remarkable +15.3% improvement in Top-3 accuracy for the MDM model. Notably, we further support a zero-shot pipeline of fine-grained motion editing, which focuses on detailed editing in both spatial and temporal dimensions via text. Dataset and code available at: CVI-SZU/FineMotion