# Appearance-Driven Automatic 3D Model Simplification

arXiv: https://arxiv.org/abs/2104.03989 · HTML: https://mlsanity.com/paper/2104.03989/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2021.

## Built on by (most cited first, 24 of 24)

- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [CLIP-Mesh: Generating textured meshes from text using pretrained image-text models](https://mlsanity.com/paper/2203.13333/) (2022)
- [Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising](https://mlsanity.com/paper/2206.03380/) (2022)
- [Flexible Isosurface Extraction for Gradient-Based Mesh Optimization](https://mlsanity.com/paper/2308.05371/) (2023)
- [Multi-View Mesh Reconstruction with Neural Deferred Shading](https://mlsanity.com/paper/2212.04386/) (2022)
- [A Survey On Text-to-3D Contents Generation In The Wild](https://mlsanity.com/paper/2405.09431/) (2024)
- [TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields](https://mlsanity.com/paper/2309.17175/) (2023)
- [DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation](https://mlsanity.com/paper/2409.07454/) (2024)
- [Filtering After Shading With Stochastic Texture Filtering](https://mlsanity.com/paper/2407.06107/) (2024)
- [Differentiable Shadow Mapping for Efficient Inverse Graphics](https://mlsanity.com/paper/2308.10896/) (2023)
- [DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification](https://mlsanity.com/paper/2603.27151/) (2026)
- [PaintHuman: Towards High-fidelity Text-to-3D Human Texturing via Denoised Score Distillation](https://mlsanity.com/paper/2310.09458/) (2023)
- [Consistent Mesh Diffusion](https://mlsanity.com/paper/2312.00971/) (2023)
- [RRM: Relightable assets using Radiance guided Material extraction](https://mlsanity.com/paper/2407.06397/) (2024)
- [Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization](https://mlsanity.com/paper/2204.01386/) (2022)
- [Automatic Testing and Validation of Level of Detail Reductions Through Supervised Learning](https://mlsanity.com/paper/2208.12674/) (2022)
- [Efficient Meshy Neural Fields for Animatable Human Avatars](https://mlsanity.com/paper/2303.12965/) (2023)
- [Efficient Scene Appearance Aggregation for Level-of-Detail Rendering](https://mlsanity.com/paper/2409.03761/) (2024)
- [PrismAvatar: Real-time animated 3D neural head avatars on edge devices](https://mlsanity.com/paper/2502.07030/) (2025)
- [Mesh Compression with Quantized Neural Displacement Fields](https://mlsanity.com/paper/2504.01027/) (2025)
- [SAGE: Semantic-Driven Adaptive Gaussian Splatting in Extended Reality](https://mlsanity.com/paper/2503.16747/) (2025)
- [Fast Voxelization and Level of Detail for Microgeometry Rendering](https://mlsanity.com/paper/2604.13191/) (2026)
- [RADmesh: Remesh-Aware Mesh Deformation](https://mlsanity.com/paper/2608.17182/) (2026)
- [Inverse Rendering for Modeling with Line Primitives](https://mlsanity.com/paper/2609.00625/) (2026)

## Abstract (arXiv)

We present a suite of techniques for jointly optimizing triangle meshes and shading models to match the appearance of reference scenes. This capability has a number of uses, including appearance-preserving simplification of extremely complex assets, conversion between rendering systems, and even conversion between geometric scene representations. We follow and extend the classic analysis-by-synthesis family of techniques: enabled by a highly efficient differentiable renderer and modern nonlinear optimization algorithms, our results are driven to minimize the image-space difference to the target scene when rendered in similar viewing and lighting conditions. As the only signals driving the optimization are differences in rendered images, the approach is highly general and versatile: it easily supports many different forward rendering models such as normal mapping, spatially-varying BRDFs, displacement mapping, etc. Supervision through images only is also key to the ability to easily convert between rendering systems and scene representations. We output triangle meshes with textured materials to ensure that the models render efficiently on modern graphics hardware and benefit from, e.g., hardware-accelerated rasterization, ray tracing, and filtered texture lookups. Our system is integrated in a small Python code base, and can be applied at high resolutions and on large models. We describe several use cases, including mesh decimation, level of detail generation, seamless mesh filtering and approximations of aggregate geometry.