# Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation arXiv: https://arxiv.org/abs/2412.13454 ยท HTML: https://mlsanity.com/paper/2412.13454/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 28 of its 44 references that are in the map. - First posted on arXiv 18 Dec 2024. ## Builds on (most cited first, 28 of 28) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019) - [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021) - [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019) - [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019) - [Hand Keypoint Detection in Single Images using Multiview Bootstrapping](https://mlsanity.com/paper/1704.07809/) (2017) - [Unsupervised Point Cloud Pre-Training via Occlusion Completion](https://mlsanity.com/paper/2010.01089/) (2020) - [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019) - [Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality](https://mlsanity.com/paper/2205.10063/) (2022) - [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021) - [SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments](https://mlsanity.com/paper/2303.09095/) (2023) - [LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors](https://mlsanity.com/paper/2205.15410/) (2022) - [Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving](https://mlsanity.com/paper/2112.12141/) (2021) - [Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection](https://mlsanity.com/paper/2207.10955/) (2022) - [STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes](https://mlsanity.com/paper/2204.01026/) (2022) - [CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions](https://mlsanity.com/paper/2303.17948/) (2023) - [Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR](https://mlsanity.com/paper/2211.16951/) (2022) - [LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment](https://mlsanity.com/paper/2402.17171/) (2024) - [HPERL: 3D Human Pose Estimation from RGB and LiDAR](https://mlsanity.com/paper/2010.08221/) (2020) - [RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method](https://mlsanity.com/paper/2403.19501/) (2024) - [LiDAR-HMR: 3D Human Mesh Recovery from LiDAR](https://mlsanity.com/paper/2311.11971/) (2023) - [MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction](https://mlsanity.com/paper/2211.13357/) (2022) - [Human-M3: A Multi-view Multi-modal Dataset for 3D Human Pose Estimation in Outdoor Scenes](https://mlsanity.com/paper/2308.00628/) (2023) - [3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels](https://mlsanity.com/paper/2306.04745/) (2023) - [LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Network](https://mlsanity.com/paper/2306.12525/) (2023) - [Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge](https://mlsanity.com/paper/2211.11983/) (2022) - [LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment](https://mlsanity.com/paper/2407.09833/) (2024) - [3D Human Pose Lifting with Grid Convolution](https://mlsanity.com/paper/2302.08760/) (2023) ## Built on by (most cited first, 5 of 5) - [VIMCAN: Visual-Inertial 3D Human Pose Estimation with Hybrid Mamba-Cross-Attention Network](https://mlsanity.com/paper/2605.07552/) (2026) - [3D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review](https://mlsanity.com/paper/2509.12197/) (2025) - [Learning Human-Object Interaction for 3D Human Pose Estimation from LiDAR Point Clouds](https://mlsanity.com/paper/2603.16343/) (2026) - [B'ezier Degradation Modeling for LiDAR-based Human Motion Capture](https://mlsanity.com/paper/2605.19620/) (2026) - [Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy](https://mlsanity.com/paper/2610.02943/) (2026) ## Abstract (arXiv) With the rapid development of autonomous driving, LiDAR-based 3D Human Pose Estimation (3D HPE) is becoming a research focus. However, due to the noise and sparsity of LiDAR-captured point clouds, robust human pose estimation remains challenging. Most of the existing methods use temporal information, multi-modal fusion, or SMPL optimization to correct biased results. In this work, we try to obtain sufficient information for 3D HPE only by modeling the intrinsic properties of low-quality point clouds. Hence, a simple yet powerful method is proposed, which provides insights both on modeling and augmentation of point clouds. Specifically, we first propose a concise and effective density-aware pose transformer (DAPT) to get stable keypoint representations. By using a set of joint anchors and a carefully designed exchange module, valid information is extracted from point clouds with different densities. Then 1D heatmaps are utilized to represent the precise locations of the keypoints. Secondly, a comprehensive LiDAR human synthesis and augmentation method is proposed to pre-train the model, enabling it to acquire a better human body prior. We increase the diversity of point clouds by randomly sampling human positions and orientations and by simulating occlusions through the addition of laser-level masks. Extensive experiments have been conducted on multiple datasets, including IMU-annotated LidarHuman26M, SLOPER4D, and manually annotated Waymo Open Dataset v2.0 (Waymo), HumanM3. Our method demonstrates SOTA performance in all scenarios. In particular, compared with LPFormer on Waymo, we reduce the average MPJPE by 10.0mm. Compared with PRN on SLOPER4D, we notably reduce the average MPJPE by 20.7mm.