Indoor environment model reconstruction has emerged as a significant and challenging task
in terms of the provision of a semantically rich and geometrically accurate indoor model …

We present an end-to-end deep learning architecture for depth map inference from multi-
view images. In the network, we first extract deep visual image features, and then build the …

We present a benchmark for image-based 3D reconstruction. The benchmark sequences
were acquired outside the lab, in realistic conditions. Ground-truth data was captured using …

We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo
reconstruction. Taking an arbitrary number of posed images as input, we first produce a set …

We propose SDFDiff, a novel approach for image-based shape optimization using
differentiable rendering of 3D shapes represented by signed distance functions (SDFs) …

Abstract 3D reconstruction of scenes using multiple images, relying on robust
correspondence search and depth estimation, has been thoroughly studied for the two‐view …

Learning-based methods are demonstrating their strong competitiveness in estimating depth
for multi-view stereo reconstruction in recent years. Among them the approaches that …

We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for
point clouds. Gradients for point locations and normals are carefully designed to handle …

Contemporary endoscopic simultaneous localization and mapping (SLAM) methods
accurately compute endoscope poses; however, they only provide a sparse 3-D …

Multi-view stereo relies on feature correspondences for 3D reconstruction, and thus is
fundamentally flawed in dealing with featureless scenes. In this paper, we propose …