# 3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels Source: [3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:29:49.256Z Authors: Zhenzhen Weng, Alexander S. Gorban, Jingwei Ji, Mahyar Najibi, Yin Zhou, Dragomir Anguelov Published: 2023-06-07T19:46:30.000Z ## Abstract Training a 3D human keypoint detector from point clouds in a supervised manner requires large volumes of high quality labels. While it is relatively easy to capture large amounts of human point clouds, annotating 3D keypoints is expensive, subjective, error prone and especially difficult for long-tail cases (pedestrians with rare poses, scooterists, etc.). In this work, we propose GC-KPL - Geometry Consistency inspired Key Point Leaning, an approach for learning 3D human joint locations from point clouds without human labels. We achieve this by our novel unsupervised loss formulations that account for the structure and movement of the human body. We show that by training on a large training set from Waymo Open Dataset without any human annotated keypoints, we are able to achieve reasonable performance as compared to the fully supervised approach. Further, the backbone benefits from the unsupervised training and is useful in downstream fewshot learning of keypoints, where fine-tuning on only 10 percent of the labeled training data gives comparable performance to fine-tuning on the entire set. We demonstrated that GC-KPL outperforms by a large margin over SoTA when trained on entire dataset and efficiently leverages large volumes of unlabeled data. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [3D Human Keypoint Estimation on Waymo Open Dataset (WOD) 1% (train)](): 3D Human Keypoint Estimation; Waymo Open Dataset (WOD) 1% (train); MPJPE (cm): 17.2. - [3D Human Keypoint Estimation on Waymo Open Dataset (WOD) 10% (train)](): 3D Human Keypoint Estimation; Waymo Open Dataset (WOD) 10% (train); MPJPE (cm): 13.4. - [3D Human Keypoint Estimation on Waymo Open Dataset (WOD) (100% train)](): 3D Human Keypoint Estimation; Waymo Open Dataset (WOD) (100% train); MPJPE (cm): 10.1. - [3D Human Keypoint Estimation on Waymo](): 3D Human Keypoint Estimation; Waymo; MPJPE: 10.1. ## Original sources and implementation [Original paper]() [PDF]()