A Multi-View High-Resolution Foot-Ankle Complex Point Cloud Dataset During Gait for Occlusion-Robust 3D Completion

2025-07-15

AI Summary

In dynamic gait analysis, high-fidelity 3D geometric reconstruction of the foot–ankle region remains challenging due to severe occlusion from the swinging limb and limited viewpoint coverage. To address this, we introduce FootGait3D—a novel, large-scale benchmark dataset specifically designed for gait scenarios, comprising 8,403 multi-view, high-resolution point cloud frames under diverse, graded occlusion conditions. FootGait3D is the first publicly available dataset enabling complete, fine-grained foot–ankle 3D reconstruction in dynamic locomotion. Data were acquired using a custom-built five-camera depth-sensing system with synchronized RGB-D capture. We comprehensively evaluate state-of-the-art single- and multi-modal point cloud completion methods—including PointTr, SnowflakeNet, SVDFormer, and PointSea—under realistic multi-view missingness. Experimental results demonstrate that our framework significantly improves geometric completion accuracy for occluded foot–ankle structures. FootGait3D establishes a reproducible, high-fidelity benchmark for biomechanical analysis, intelligent prosthetic design, and legged robotic modeling.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance

Abstract

The kinematics analysis of foot-ankle complex during gait is essential for advancing biomechanical research and clinical assessment. Collecting accurate surface geometry data from the foot and ankle during dynamic gait conditions is inherently challenging due to swing foot occlusions and viewing limitations. Thus, this paper introduces FootGait3D, a novel multi-view dataset of high-resolution ankle-foot surface point clouds captured during natural gait. Different from existing gait datasets that typically target whole-body or lower-limb motion, FootGait3D focuses specifically on the detailed modeling of the ankle-foot region, offering a finer granularity of motion data. To address this, FootGait3D consists of 8,403 point cloud frames collected from 46 subjects using a custom five-camera depth sensing system. Each frame includes a complete 5-view reconstruction of the foot and ankle (serving as ground truth) along with partial point clouds obtained from only four, three, or two views. This structured variation enables rigorous evaluation of 3D point cloud completion methods under varying occlusion levels and viewpoints. Our dataset is designed for shape completion tasks, facilitating the benchmarking of state-of-the-art single-modal (e.g., PointTr, SnowflakeNet, Anchorformer) and multi-modal (e.g., SVDFormer, PointSea, CSDN) completion networks on the challenge of recovering the full foot geometry from occluded inputs. FootGait3D has significant potential to advance research in biomechanics and multi-segment foot modeling, offering a valuable testbed for clinical gait analysis, prosthetic design, and robotics applications requiring detailed 3D models of the foot during motion. The dataset is now available at https://huggingface.co/datasets/ljw285/FootGait3D.

Problem

• Address occlusion challenges in foot-ankle 3D data during gait.
• Provide high-resolution multi-view dataset for detailed foot modeling.
• Enable robust 3D completion methods for occluded foot geometry.

Innovation

• Multi-view high-resolution ankle-foot point clouds
• Custom five-camera depth sensing system
• Structured occlusion for completion benchmarking