journal article

Journal Article

Text

Image and Vision Computing. 2025, 164, p. 105793

Simultaneous acquisition of geometry and material for translucent objects

Elsevier Ltd

English

Text

2025-10-24

https://doi.org/10.1016/j.imavis.2025.105793

Li C., Ngo T.T., Nagahara H.. Simultaneous acquisition of geometry and material for translucent objects. Image and Vision Computing 164, 105793 (2025); https://doi.org/10.1016/j.imavis.2025.105793.

Reconstructing the geometry and material properties of translucent objects from images is a challenging problem due to the complex light propagation of translucent media and the inherent ambiguity of inverse rendering. Therefore, previous works often make the assumption that the objects are opaque or use a simplified model to describe translucent objects, which significantly affects the reconstruction quality and limits the downstream tasks such as relighting or material editing. We present a novel framework that tackles this challenge through a combination of physically grounded and data-driven strategies. At the core of our approach is a hybrid rendering supervision scheme that fuses a differentiable physical renderer with a learned neural renderer to guide reconstruction. To further enhance supervision, we introduce an augmented loss tailored to the neural renderer. Our system takes as input a flash/no-flash image pair, enabling it to disambiguate complex light propagation that happens inside translucent objects. We train our model on a large-scale synthetic dataset of 117 K scenes and evaluate across both synthetic benchmarks and real-world captures. To mitigate the domain gap between synthetic and real data, we contribute a new real-world dataset with ground-truth surface normals and fine-tune our model accordingly. Extensive experiments validate the robustness and accuracy of our method across diverse scenarios.

This article is licensed under a Creative Commons Attribution 4.0 International License.

103519

Simultaneous acquisition of geometry and material for translucent objects

Elsevier Ltd

English

2025-10-24

Image and Vision Computing

164

105793

https://doi.org/10.1016/j.imavis.2025.105793

https://hdl.handle.net/11094/103519