Semantic Image Translation for Repairing the Texture Defects of Building Models

The accurate representation of 3-D building models in urban environments is significantly hindered by challenges such as texture occlusion, blurring, and missing details, which are difficult to mitigate through standard photogrammetric texture mapping pipelines. Current image completion methods often struggle to produce structured results and effectively handle the intricate nature of highly structured facade textures with diverse architectural styles. Furthermore, existing image synthesis methods encounter difficulties in preserving high-frequency details and artificial regular structures, which are essential for achieving realistic facade texture synthesis. To address these challenges, we introduce a novel approach for synthesizing facade texture images that authentically reflect the architectural style from a structured label map, guided by a ground-truth facade image. In order to preserve fine details and regular structures, we propose a regularity-aware multidomain method that capitalizes on frequency information and corner maps. We also incorporate semantic region-adaptive normalization (SEAN) blocks into our generator to enable versatile style transfer. To generate plausible structured images without undesirable regions, we employ image completion techniques to remove occlusions according to semantics prior to image inference. Our proposed method is also capable of synthesizing texture images with specific styles for facades that lack preexisting textures, using manually annotated labels. Experimental results on publicly available facade image and 3-D model datasets demonstrate that our method yields superior results and effectively addresses issues associated with flawed textures.