# Physics-Based Inverse Rendering using Combined Implicit and Explicit Geometries

arXiv: https://arxiv.org/abs/2205.01242 · HTML: https://mlsanity.com/paper/2205.01242/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2022.

## Built on by (most cited first, 14 of 14)

- [GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization](https://mlsanity.com/paper/2312.05133/) (2023)
- [TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion](https://mlsanity.com/paper/2401.09416/) (2024)
- [Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark](https://mlsanity.com/paper/2310.16044/) (2023)
- [Neural-PBIR Reconstruction of Shape, Material, and Illumination](https://mlsanity.com/paper/2304.13445/) (2023)
- [Relighting Neural Radiance Fields with Shadow and Highlight Hints](https://mlsanity.com/paper/2308.13404/) (2023)
- [Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset](https://mlsanity.com/paper/2504.08541/) (2025)
- [3D Reconstruction with Fast Dipole Sums](https://mlsanity.com/paper/2405.16788/) (2024)
- [Differentiable Point-based Inverse Rendering](https://mlsanity.com/paper/2312.02480/) (2023)
- [A Simple Approach to Differentiable Rendering of SDFs](https://mlsanity.com/paper/2405.08733/) (2024)
- [DPCS: Path Tracing-Based Differentiable Projector-Camera Systems](https://mlsanity.com/paper/2503.12174/) (2025)
- [Detachable Novel Views Synthesis of Dynamic Scenes Using Distribution-Driven Neural Radiance Fields](https://mlsanity.com/paper/2301.00411/) (2023)
- [PBIR-NIE: Glossy Object Capture under Non-Distant Lighting](https://mlsanity.com/paper/2408.06878/) (2024)
- [RNA: Relightable Neural Assets](https://mlsanity.com/paper/2312.09398/) (2023)
- [Automated design of compound lenses with discrete-continuous optimization](https://mlsanity.com/paper/2509.23572/) (2025)

## Abstract (arXiv)

Mathematically representing the shape of an object is a key ingredient for solving inverse rendering problems. Explicit representations like meshes are efficient to render in a differentiable fashion but have difficulties handling topology changes. Implicit representations like signed-distance functions, on the other hand, offer better support of topology changes but are much more difficult to use for physics-based differentiable rendering. We introduce a new physics-based inverse rendering pipeline that uses both implicit and explicit representations. Our technique enjoys the benefit of both representations by supporting both topology changes and differentiable rendering of complex effects such as environmental illumination, soft shadows, and interreflection. We demonstrate the effectiveness of our technique using several synthetic and real examples.