mlsanityData to 7 Oct 2026

Semantic UV mapping to improve texture inpainting for indoor scenes

arXiv 2407.09248 ↗First posted 12 Jul 2024cs.CVcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

23 of 30 references.

References · 23

  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  2. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  3. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  4. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  5. 2023Inpaint Anything: Segment Anything Meets Image Inpaintingcited by 233
  6. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 216
  7. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  8. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  9. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  10. 2023SAI3D: Segment Any Instance in 3D Scenescited by 90
  11. 2023NeRFiller: Completing Scenes via Generative 3D Inpaintingcited by 62
  12. 2022AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesiscited by 39
11 more
  1. 2023V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detectioncited by 34
  2. 2023UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenescited by 31
  3. 2023Nuvo: Neural UV Mapping for Unruly 3D Representationscited by 29
  4. 2024Flatten Anything: Unsupervised Neural Surface Parameterizationcited by 15
  5. 2020No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometrycited by 9
  6. 2023Clutter Detection and Removal in 3D Scenes with View-Consistent Inpaintingcited by 9
  7. 2019VoteNet+ : An Improved Deep Learning Label Fusion Method for Multi-atlas Segmentationcited by 4
  8. 2020GraphSeam: Supervised Graph Learning Framework for Semantic UV Mappingcited by 4
  9. 2021Towards Full-to-Empty Room Generation with Structure-Aware Feature Encoding and Soft Semantic Region-Adaptive Normalizationcited by 4
  10. 2024An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramascited by 4
  11. 2018Latent RANSACcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectivescited by 1