Synthetic Dataset Generation for Partially Observed Indoor Objects

2026-04-08

AI Summary

Existing learning-based methods for 3D scene reconstruction and object completion are hindered by the scarcity of large-scale, ground-truth-complete datasets of partial scans, as real-world scans inherently lack geometric ground truth in occluded regions. To address this limitation, this work proposes V-Scan, a Unity-based virtual scanning framework that innovatively integrates procedural indoor scene generation with configurable ray-casting simulation to faithfully replicate sensor viewpoints, occlusion effects, and noise characteristics. The framework simultaneously produces synthetic data comprising colorized partial point clouds, voxelized occlusion masks, and complete geometric ground truth. This dataset provides high-quality supervisory signals for 3D reconstruction and completion tasks, substantially facilitating the training and evaluation of relevant learning-based models.

Abstract

Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is costly and time-consuming, particularly when accurate ground truth for occluded regions is required. In this work, we present a virtual scanning framework implemented in Unity for generating realistic synthetic 3D scan datasets. The proposed system simulates the behaviour of real-world scanners using configurable parameters such as scan resolution, measurement range, and distance-dependent noise. Instead of directly sampling mesh surfaces, the framework performs ray-based scanning from virtual viewpoints, enabling realistic modelling of sensor visibility and occlusion effects. In addition, panoramic images captured at the scanner location are used to assign colours to the resulting point clouds. To support scalable dataset creation, the scanner is integrated with a procedural indoor scene generation pipeline that automatically produces diverse room layouts and furniture arrangements. Using this system, we introduce the \textit{V-Scan} dataset, which contains synthetic indoor scans together with object-level partial point clouds, voxel-based occlusion grids, and complete ground-truth geometry. The resulting dataset provides valuable supervision for training and evaluating learning-based methods for scene reconstruction and object completion.

Problem

• 3D scene reconstruction
• object completion
• synthetic dataset
• partial observation
• ground-truth geometry

Innovation

• synthetic dataset generation
• virtual scanning
• ray-based occlusion modeling
• procedural scene generation
• 3D object completion