Structure-Preserving Reshape for Textured Architectural Scenes

Transductive Segmentation of Textured Meshes

This paper addresses the problem of segmenting a textured mesh into objects or object classes, consistently with user-supplied seeds. We view this task as transductive learning and use the flexibility of kernel-based weights to incorporate a various number of diverse features. Our method combines a Laplacian graph regularizer that enforces spatial coherence in label propagation and an SVM class...

Efficient Dense Matching for Textured Scenes using Region Growing

We present a simple and efficient dense matching method based on region growing techniques, which can be applied to a wide range of globally textured images like many outdoor scenes. Our method can deal with non-rigid scenes and large camera motions. First a few highly distinctive features like points or areas are extracted and matched. These initial matches are then used in a correlation-based...

Reconstructing Polyhedral Models of Architectural Scenes from Photographs

This paper presents a new image-based modeling method that facilitates the recovery of accurate polyhedral models of architectural scenes. The method is particularly e ective because it exploits many of the constraints that are characteristic of architectural scenes. This work is placed in the context of the Fa cade project, whose goal is to use images to produce photo-realistic novel views of ...

Towards unsupervised reconstruction of architectural models

Architectural blueprints offer a concise, clear and high-level description of the structure of a building. On the other hand, state of the art reconstruction pipelines can nowadays produce dense point clouds or high-polygon meshes without any human intervention from a set of digital images or video. We present a fully automated structure and motion framework capable of capturing the expressivit...

Robust Wide-Baseline Stereo Matching for Sparsely Textured Scenes