PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911110427312128 |
|---|---|
| author | Ye, Yuyan Xu, Hang Huang, Yanghang Huang, Jiali Weng, Qian |
| author_facet | Ye, Yuyan Xu, Hang Huang, Yanghang Huang, Jiali Weng, Qian |
| contents | This paper proposes PreSem-Surf, an optimized method based on the Neural Radiance Field (NeRF) framework, capable of reconstructing high-quality scene surfaces from RGB-D sequences in a short time. The method integrates RGB, depth, and semantic information to improve reconstruction performance. Specifically, a novel SG-MLP sampling structure combined with PR-MLP (Preconditioning Multilayer Perceptron) is introduced for voxel pre-rendering, allowing the model to capture scene-related information earlier and better distinguish noise from local details. Furthermore, progressive semantic modeling is adopted to extract semantic information at increasing levels of precision, reducing training time while enhancing scene understanding. Experiments on seven synthetic scenes with six evaluation metrics show that PreSem-Surf achieves the best performance in C-L1, F-score, and IoU, while maintaining competitive results in NC, Accuracy, and Completeness, demonstrating its effectiveness and practical applicability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13228 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism Ye, Yuyan Xu, Hang Huang, Yanghang Huang, Jiali Weng, Qian Graphics Artificial Intelligence Computer Vision and Pattern Recognition Image and Video Processing This paper proposes PreSem-Surf, an optimized method based on the Neural Radiance Field (NeRF) framework, capable of reconstructing high-quality scene surfaces from RGB-D sequences in a short time. The method integrates RGB, depth, and semantic information to improve reconstruction performance. Specifically, a novel SG-MLP sampling structure combined with PR-MLP (Preconditioning Multilayer Perceptron) is introduced for voxel pre-rendering, allowing the model to capture scene-related information earlier and better distinguish noise from local details. Furthermore, progressive semantic modeling is adopted to extract semantic information at increasing levels of precision, reducing training time while enhancing scene understanding. Experiments on seven synthetic scenes with six evaluation metrics show that PreSem-Surf achieves the best performance in C-L1, F-score, and IoU, while maintaining competitive results in NC, Accuracy, and Completeness, demonstrating its effectiveness and practical applicability. |
| title | PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism |
| topic | Graphics Artificial Intelligence Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2508.13228 |