A deep learning-based 3D reconstruction framework for Hongcun village using cultural-spatial attention networks

Semantic Segmentation-Guided Reconstruction and Artistic Style Synthesis of Intangible Cultural Heritage Patterns Using a Deep Learning Framework.

The digital preservation and reconstruction of intangible cultural heritage (ICH) patterns have attracted increasing attention with the advancement of deep learning-based image synthesis techniques. Existing SegCycle-SPADE-based approaches have demonstrated potential for the structural segmentation and artistic reconst...

A hybrid framework for 3D reconstruction and semantic analysis using NeRF

Digital Reconstruction and Cross-Cultural Knowledge Service of Lingnan Garden Heritage

Experimental results demonstrated that the integrated framework significantly improves geometric-texture alignment, reduces system rendering delay, and effectively extends user engagement and learning experience.

Simulation of Natural Landscapes Using Deep Learning and VR Rendering Models in Digital Art for Modern Historic Buildings

This technical reappraisal reconstructs a two-stage deep-learning workflow for semantic analysis and visual rendering of landscape architectural plans. The intended pipeline uses a fully convolutional network (FCN) to assign labelled pixels to 11 landscape categories and then applies a cycle-consistent generative adver...

CSRF: A Robust 3D Reconstruction Framework for Crowdsourced Street View Videos

Crowdsourced Radiance Fields (CSRF), a framework designed to harness CSVVs, substantially expands the potential data source for 3D environment reconstruction using street view videos, while the CS3D100 benchmark establishes a robust foundation for future improvements in this direction.

Three-Dimensional (3D) Semantic Reconstruction of Complex Historical Buildings Based on Multi-Source UAV Images and Deep Learning GAN Model

Existing reconstruction methods commonly face practical bottlenecks such as ambiguous feature matching, disjointed geometric semantic information, and insufficient controllability of generated texture styles when dealing with programmatic complex historical buildings. Therefore, it is necessary to conduct research on c...