LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model
This work addresses the need for more generalizable human keypoint localization models in computer vision, offering a novel approach that leverages language clues, though it is incremental in applying LLMs to this specific task.
The authors tackled the problem of limited generalization in human keypoint localization by proposing LocLLM, a model that uses images and text instructions to output keypoint coordinates, achieving remarkable performance on standard 2D/3D benchmarks and showing superior flexibility in cross-dataset localization and detecting novel keypoints.
The capacity of existing human keypoint localization models is limited by keypoint priors provided by the training data. To alleviate this restriction and pursue more general model, this work studies keypoint localization from a different perspective by reasoning locations based on keypiont clues in text descriptions. We propose LocLLM, the first Large-Language Model (LLM) based keypoint localization model that takes images and text instructions as inputs and outputs the desired keypoint coordinates. LocLLM leverages the strong reasoning capability of LLM and clues of keypoint type, location, and relationship in textual descriptions for keypoint localization. To effectively tune LocLLM, we construct localization-based instruction conversations to connect keypoint description with corresponding coordinates in input image, and fine-tune the whole model in a parameter-efficient training pipeline. LocLLM shows remarkable performance on standard 2D/3D keypoint localization benchmarks. Moreover, incorporating language clues into the localization makes LocLLM show superior flexibility and generalizable capability in cross dataset keypoint localization, and even detecting novel type of keypoints unseen during training.