# Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container

arXiv: https://arxiv.org/abs/2303.13805 · HTML: https://mlsanity.com/paper/2303.13805/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 11 of 11)

- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [SAL: Sign Agnostic Learning of Shapes from Raw Data](https://mlsanity.com/paper/1911.10414/) (2019)
- [NeRFReN: Neural Radiance Fields with Reflections](https://mlsanity.com/paper/2111.15234/) (2021)
- [Neural 3D Reconstruction in the Wild](https://mlsanity.com/paper/2205.12955/) (2022)
- [Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes](https://mlsanity.com/paper/2004.10904/) (2020)
- [Full 3D Reconstruction of Transparent Objects](https://mlsanity.com/paper/1805.03482/) (2018)
- [Differentiable Refraction-Tracing for Mesh Reconstruction of Transparent Objects](https://mlsanity.com/paper/2009.09144/) (2020)
- [Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction](https://mlsanity.com/paper/2105.09993/) (2021)

## Built on by (most cited first, 10 of 10)

- [Neural Radiance Fields for the Real World: A Survey](https://mlsanity.com/paper/2501.13104/) (2025)
- [LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow](https://mlsanity.com/paper/2409.05688/) (2024)
- [GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction](https://mlsanity.com/paper/2506.13110/) (2025)
- [Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation](https://mlsanity.com/paper/2503.11633/) (2025)
- [L0-Sampler: An L0 Model Guided Volume Sampling for NeRF](https://mlsanity.com/paper/2311.07044/) (2023)
- [REF2-NeRF: Reflection and Refraction aware Neural Radiance Field](https://mlsanity.com/paper/2311.17116/) (2023)
- [From Transparent to Opaque: Rethinking Neural Implicit Surfaces with α-NeuS](https://mlsanity.com/paper/2411.05362/) (2024)
- [RefRef: A Dataset and Benchmark for Reconstructing Refractive and Reflective Objects](https://mlsanity.com/paper/2505.05848/) (2025)
- [RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing](https://mlsanity.com/paper/2603.21695/) (2026)
- [SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping](https://mlsanity.com/paper/2605.28735/) (2026)

## Abstract (arXiv)

In this paper, we define a new problem of recovering the 3D geometry of an object confined in a transparent enclosure. We also propose a novel method for solving this challenging problem. Transparent enclosures pose challenges of multiple light reflections and refractions at the interface between different propagation media e.g. air or glass. These multiple reflections and refractions cause serious image distortions which invalidate the single viewpoint assumption. Hence the 3D geometry of such objects cannot be reliably reconstructed using existing methods, such as traditional structure from motion or modern neural reconstruction methods. We solve this problem by explicitly modeling the scene as two distinct sub-spaces, inside and outside the transparent enclosure. We use an existing neural reconstruction method (NeuS) that implicitly represents the geometry and appearance of the inner subspace. In order to account for complex light interactions, we develop a hybrid rendering strategy that combines volume rendering with ray tracing. We then recover the underlying geometry and appearance of the model by minimizing the difference between the real and hybrid rendered images. We evaluate our method on both synthetic and real data. Experiment results show that our method outperforms the state-of-the-art (SOTA) methods. Codes and data will be available at https://github.com/hirotong/ReNeuS