HolmeSketcher: Generative 3D Sketch Mapping for Spatial Reconstruction in Crime Scene Investigation

2026-04-20

AI Summary

Traditional crime scene investigation (CSI) relies on two-dimensional sketches, which struggle to accurately convey three-dimensional spatial relationships, thereby limiting the fidelity and interpretability of scene reconstructions. This work proposes a generative 3D sketch mapping system tailored for CSI that integrates generative artificial intelligence with extended reality (XR) interaction for the first time. The system comprises an XR-based front-end drawing interface and a back-end pipeline powered by deep learning for 3D object generation and scene reconstruction. User studies demonstrate that the system significantly enhances both the spatial accuracy and interpretability of reconstructed scenes. Building on these findings, the study articulates design principles for next-generation CSI-specific 3D sketching tools and reveals a critical trade-off between task load and system usability.

Technology Category

• Computer Vision: 3D Computer Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Sketch mapping is widely used in crime scene investigation (CSI) to document, interpret, and communicate spatial information. However, it is typically performed on 2D media, which limits its ability to represent 3D spatial relationships. We present HolmeSketcher, a generative 3D sketch mapping system that combines a front-end 3D drawing interface with a back-end deep learning pipeline to support object generation and scene reconstruction in extended reality. In a within-subject user study (N = 15), HolmeSketcher improved the spatial accuracy and interpretability of reconstructed scenes, but with a clear trade-off of higher task load and lower usability compared with paper-based 2D sketch mapping. By integrating findings from the user study and expert interviews (N = 3), we further derive three design implications for next-generation 3D sketch mapping tools for CSI.

Problem

• crime scene investigation
• 3D sketch mapping
• spatial reconstruction
• spatial relationships
• 2D sketching

Innovation

• generative 3D sketching
• spatial reconstruction
• crime scene investigation
• extended reality
• deep learning pipeline