PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism
This work addresses the need for efficient and accurate 3D surface reconstruction for applications like robotics or AR/VR, though it appears incremental as it builds upon the existing NeRF framework with enhancements.
The paper tackles the problem of reconstructing high-quality scene surfaces from RGB-D sequences by proposing PreSem-Surf, an optimized NeRF-based method that integrates RGB, depth, and semantic information, achieving best performance in C-L1, F-score, and IoU metrics on synthetic scenes.
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.