Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset

TL;DR

The Digital Twin Catalog (DTC) addresses the lack of large-scale, real-world digital twin datasets by providing 2,000 mm-accurate 3D object models with photorealistic PBR materials and paired DSLR and egocentric evaluation data. It benchmarks state-of-the-art object reconstruction and inverse rendering methods, and demonstrates the practical value of high-fidelity digital twins for robotics through simulated pushing and grasping tasks. The dataset enables robust evaluation of geometry, relighting, and novel-view synthesis under diverse lighting and viewing conditions, and supports future agnostic AR/VR and sim-to-real transfer research. The work highlights both the performance gains achievable with digital-twin fidelity and the current bottlenecks in automation and material handling for scalable twin-generation.

Abstract

We introduce the Digital Twin Catalog (DTC), a new large-scale photorealistic 3D object digital twin dataset. A digital twin of a 3D object is a highly detailed, virtually indistinguishable representation of a physical object, accurately capturing its shape, appearance, physical properties, and other attributes. Recent advances in neural-based 3D reconstruction and inverse rendering have significantly improved the quality of 3D object reconstruction. Despite these advancements, there remains a lack of a large-scale, digital twin-quality real-world dataset and benchmark that can quantitatively assess and compare the performance of different reconstruction methods, as well as improve reconstruction quality through training or fine-tuning. Moreover, to democratize 3D digital twin creation, it is essential to integrate creation techniques with next-generation egocentric computing platforms, such as AR glasses. Currently, there is no dataset available to evaluate 3D object reconstruction using egocentric captured images. To address these gaps, the DTC dataset features 2,000 scanned digital twin-quality 3D objects, along with image sequences captured under different lighting conditions using DSLR cameras and egocentric AR glasses. This dataset establishes the first comprehensive real-world evaluation benchmark for 3D digital twin creation tasks, offering a robust foundation for comparing and improving existing reconstruction methods. The DTC dataset is already released at https://www.projectaria.com/datasets/dtc/ and we will also make the baseline evaluations open-source.

Figures (21)

• Figure 1: Example DTC models with photorealistic PBR materials.
• Figure 2: 3D object scanner by Covision Media®.
• Figure 3: Rendered DTC models (left) v.s. Photo (Right).
• Figure 4: Shape and material (albedo) quality comparison between Stanford-ORB kuang2023stanfordorb (left) and our DTC (right).
• Figure 5: DSLR rig for capturing evaluation data.