# Semantic UV mapping to improve texture inpainting for indoor scenes

arXiv: https://arxiv.org/abs/2407.09248 · HTML: https://mlsanity.com/paper/2407.09248/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 12 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Inpaint Anything: Segment Anything Meets Image Inpainting](https://mlsanity.com/paper/2304.06790/) (2023)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [Texture Fields: Learning Texture Representations in Function Space](https://mlsanity.com/paper/1905.07259/) (2019)
- [AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation](https://mlsanity.com/paper/2203.09516/) (2022)
- [ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans](https://mlsanity.com/paper/1712.10215/) (2017)
- [SAI3D: Segment Any Instance in 3D Scenes](https://mlsanity.com/paper/2312.11557/) (2023)
- [NeRFiller: Completing Scenes via Generative 3D Inpainting](https://mlsanity.com/paper/2312.04560/) (2023)
- [AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis](https://mlsanity.com/paper/2204.03105/) (2022)
- [V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection](https://mlsanity.com/paper/2308.04409/) (2023)
- [UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes](https://mlsanity.com/paper/2303.14541/) (2023)
- [Nuvo: Neural UV Mapping for Unruly 3D Representations](https://mlsanity.com/paper/2312.05283/) (2023)
- [Flatten Anything: Unsupervised Neural Surface Parameterization](https://mlsanity.com/paper/2405.14633/) (2024)
- [No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry](https://mlsanity.com/paper/2012.10565/) (2020)
- [Clutter Detection and Removal in 3D Scenes with View-Consistent Inpainting](https://mlsanity.com/paper/2304.03763/) (2023)
- [VoteNet+ : An Improved Deep Learning Label Fusion Method for Multi-atlas Segmentation](https://mlsanity.com/paper/1911.00582/) (2019)
- [GraphSeam: Supervised Graph Learning Framework for Semantic UV Mapping](https://mlsanity.com/paper/2011.13748/) (2020)
- [Towards Full-to-Empty Room Generation with Structure-Aware Feature Encoding and Soft Semantic Region-Adaptive Normalization](https://mlsanity.com/paper/2112.05396/) (2021)
- [An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramas](https://mlsanity.com/paper/2405.03682/) (2024)
- [Latent RANSAC](https://mlsanity.com/paper/1802.07045/) (2018)

## Built on by (most cited first, 1 of 1)

- [Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives](https://mlsanity.com/paper/2509.25094/) (2025)

## Abstract (arXiv)

This work aims to improve texture inpainting after clutter removal in scanned indoor meshes. This is achieved with a new UV mapping pre-processing step which leverages semantic information of indoor scenes to more accurately match the UV islands with the 3D representation of distinct structural elements like walls and floors. Semantic UV Mapping enriches classic UV unwrapping algorithms by not only relying on geometric features but also visual features originating from the present texture. The segmentation improves the UV mapping and simultaneously simplifies the 3D geometric reconstruction of the scene after the removal of loose objects. Each segmented element can be reconstructed separately using the boundary conditions of the adjacent elements. Because this is performed as a pre-processing step, other specialized methods for geometric and texture reconstruction can be used in the future to improve the results even further.