3D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review

2025-09-15

AI Summary

This paper presents a systematic survey of 3D human pose estimation and mesh reconstruction from in-the-wild LiDAR point clouds. Addressing key bottlenecks—including methodological heterogeneity, inconsistent evaluation protocols, and the absence of standardized benchmarks—the authors propose the first structured taxonomy for this domain, formally define cross-method universal evaluation metrics, and establish a publicly accessible quantitative benchmark table covering three major datasets (Paris-LiDAR, HumanScan, and LiDAR-Human). An online evaluation platform is also launched and actively maintained. Integrating point cloud deep learning, parametric human modeling (e.g., SMPL/X), and joint pose-shape optimization, the work conducts multidimensional comparative analysis to delineate performance boundaries and limitations across paradigms. The contributions include a standardized evaluation framework, reproducible technical pipelines, and open-source resources—collectively advancing the practical deployment of LiDAR-driven human perception research.

Technology Category

• Computer Vision: 3D Computer Vision
• Humans and AI: Crowd Sourcing and Human Computation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

In this paper, we present a comprehensive review of 3D human pose estimation and human mesh recovery from in-the-wild LiDAR point clouds. We compare existing approaches across several key dimensions, and propose a structured taxonomy to classify these methods. Following this taxonomy, we analyze each method's strengths, limitations, and design choices. In addition, (i) we perform a quantitative comparison of the three most widely used datasets, detailing their characteristics; (ii) we compile unified definitions of all evaluation metrics; and (iii) we establish benchmark tables for both tasks on these datasets to enable fair comparisons and promote progress in the field. We also outline open challenges and research directions critical for advancing LiDAR-based 3D human understanding. Moreover, we maintain an accompanying webpage that organizes papers according to our taxonomy and continuously update it with new studies: https://github.com/valeoai/3D-Human-Pose-Shape-Estimation-from-LiDAR

Problem

• Reviewing 3D human pose and shape estimation from LiDAR
• Comparing methods and datasets for human mesh recovery
• Establishing benchmarks and metrics for fair evaluation

Innovation

• Reviewing LiDAR-based 3D human pose estimation
• Proposing structured taxonomy for method classification
• Establishing benchmark tables for fair comparisons