Repetition-based dense single-view reconstruction

TLDR

The study proposes a novel single‑view dense reconstruction method for repetitive scene structures. The method models shape recovery as dense pixel correspondences within a single image using interval maps, introduces a repetition constraint to enforce consistency, and applies a graph‑cut optimization to balance geometric repetition with photometric and spatial smoothness. Experiments demonstrate accurate reconstruction of dense 3D repetitive structures, proving robustness to outliers such as structure variations, illumination changes, and occlusions.

Abstract

This paper presents a novel approach for dense reconstruction from a single-view of a repetitive scene structure. Given an image and its detected repetition regions, we model the shape recovery as the dense pixel correspondences within a single image. The correspondences are represented by an interval map that tells the distance of each pixel to its matched pixels within the single image. In order to obtain dense repetitive structures, we develop a new repetition constraint that penalizes the inconsistency between the repetition intervals of the dynamically corresponding pixel pairs. We deploy a graph-cut to balance between the high-level constraint of geometric repetition and the low-level constraints of photometric consistency and spatial smoothness. We demonstrate the accurate reconstruction of dense 3D repetitive structures through a variety of experiments, which prove the robustness of our approach to outliers such as structure variations, illumination changes, and occlusions.