PoseScript: Linking 3D Human Poses and Natural Language
Preprint
Abstract
Natural language plays a critical role in many computer vision applications, such as image captioning, visual question answering, and cross-modal retrieval, to provide fine-grained semantic information. Unfortunately, while human pose is key to human understanding, current 3D human pose datasets lack detailed language descriptions. To address this issue, we have introduced the PoseScript dataset. This dataset pairs more than six thousand 3D human poses from AMASS with rich human-annotated descriptions of the body parts and their spatial relationships. Additionally, to increase the size of the dataset to a scale that is compatible with data-hungry learning algorithms, we have proposed an elaborate captioning process that generates automatic synthetic descriptions in natural language from given 3D keypoints. This process extracts low-level pose information, known as "posecodes", using a set of simple but generic rules on the 3D keypoints. These posecodes are then combined into higher level textual descriptions using syntactic rules. With automatic annotations, the amount of available data significantly scales up (100k), making it possible to effectively pretrain deep models for finetuning on human captions. To showcase the potential of annotated poses, we present three multi-modal learning tasks that utilize the PoseScript dataset. Firstly, we develop a pipeline that maps 3D poses and textual descriptions into a joint embedding space, allowing for cross-modal retrieval of relevant poses from large-scale datasets. Secondly, we establish a baseline for a text-conditioned model generating 3D poses. Thirdly, we present a learned process for generating pose descriptions. These applications demonstrate the versatility and usefulness of annotated poses in various tasks and pave the way for future research in the field.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- PoseScript: 3D Human Poses from Natural Language2022
- CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes2022
- TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts2022
- MotionCLIP: Exposing Human Motion Generation to CLIP Space2022
- TEMOS: Generating Diverse Human Motions from Textual Descriptions2022
- StyleGAN-Human: A Data-Centric Odyssey of Human Generation2022
- Adversarial Synthesis of Human Pose from Text2021
- ScanRefer: 3D Object Localization in RGB-D Scans Using Natural Language2020
- Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings2019
- Microsoft COCO: Common Objects in Context2014