# TensoSDF: Roughness-aware Tensorial Representation for Robust Geometry and Material Reconstruction

arXiv: https://arxiv.org/abs/2402.02771 · HTML: https://mlsanity.com/paper/2402.02771/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2024.

## Built on by (most cited first, 26 of 26)

- [Ref-GS: Directional Factorization for 2D Gaussian Splatting](https://mlsanity.com/paper/2412.00905/) (2024)
- [MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference](https://mlsanity.com/paper/2510.11387/) (2025)
- [RNG: Relightable Neural Gaussians](https://mlsanity.com/paper/2409.19702/) (2024)
- [TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians](https://mlsanity.com/paper/2504.18768/) (2025)
- [GlossyGS: Inverse Rendering of Glossy Objects with 3D Gaussian Splatting](https://mlsanity.com/paper/2410.13349/) (2024)
- [Gaussian Splatting with Discretized SDF for Relightable Assets](https://mlsanity.com/paper/2507.15629/) (2025)
- [GS-ROR2: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction](https://mlsanity.com/paper/2406.18544/) (2024)
- [GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction](https://mlsanity.com/paper/2506.13110/) (2025)
- [RTR-GS: 3D Gaussian Splatting for Inverse Rendering with Radiance Transfer and Reflection](https://mlsanity.com/paper/2507.07733/) (2025)
- [PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction](https://mlsanity.com/paper/2509.19726/) (2025)
- [Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis](https://mlsanity.com/paper/2505.21502/) (2025)
- [UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors](https://mlsanity.com/paper/2605.00658/) (2026)
- [MatMart: Material Reconstruction of 3D Objects via Diffusion](https://mlsanity.com/paper/2511.18900/) (2025)
- [Radiometrically Consistent Gaussian Surfels for Inverse Rendering](https://mlsanity.com/paper/2603.01491/) (2026)
- [Material Transforms from Disentangled NeRF Representations](https://mlsanity.com/paper/2411.08037/) (2024)
- [TexHOI: Reconstructing Textures of 3D Unknown Objects in Monocular Hand-Object Interaction Scenes](https://mlsanity.com/paper/2501.03525/) (2025)
- [WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Rendering](https://mlsanity.com/paper/2512.11237/) (2025)
- [GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space](https://mlsanity.com/paper/2605.00498/) (2026)
- [DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation](https://mlsanity.com/paper/2509.07435/) (2025)
- [GS-2M: Material-aware Gaussian Splatting for High-fidelity Mesh Reconstruction](https://mlsanity.com/paper/2509.22276/) (2025)
- [Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction](https://mlsanity.com/paper/2511.21098/) (2025)
- [Ref-DGS: Reflective Dual Gaussian Splatting](https://mlsanity.com/paper/2603.07664/) (2026)
- [PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction](https://mlsanity.com/paper/2603.10801/) (2026)
- [SRUG: Shadow-Guided Relightable Urban Scene with Generation Model](https://mlsanity.com/paper/2605.24700/) (2026)
- [Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition](https://mlsanity.com/paper/2607.09329/) (2026)
- [Plenoptic Condensation: A Novel Approach to Generalized Scene Reconstruction](https://mlsanity.com/paper/2607.18151/) (2026)

## Abstract (arXiv)

Reconstructing objects with realistic materials from multi-view images is problematic, since it is highly ill-posed. Although the neural reconstruction approaches have exhibited impressive reconstruction ability, they are designed for objects with specific materials (e.g., diffuse or specular materials). To this end, we propose a novel framework for robust geometry and material reconstruction, where the geometry is expressed with the implicit signed distance field (SDF) encoded by a tensorial representation, namely TensoSDF. At the core of our method is the roughness-aware incorporation of the radiance and reflectance fields, which enables a robust reconstruction of objects with arbitrary reflective materials. Furthermore, the tensorial representation enhances geometry details in the reconstructed surface and reduces the training time. Finally, we estimate the materials using an explicit mesh for efficient intersection computation and an implicit SDF for accurate representation. Consequently, our method can achieve more robust geometry reconstruction, outperform the previous works in terms of relighting quality, and reduce 50% training times and 70% inference time.