Multi-view stereo infers the 3D geometry from a set of images captured from several known
positions and viewpoints. It is one of the most important components of 3D reconstruction …

Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera
intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain yet …

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

Image Matching is a core component of all best-performing algorithms and pipelines in 3D
vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to …

We present GeoNeRF, a generalizable photorealistic novel view synthesis method based on
neural radiance fields. Our approach consists of two main stages: a geometry reasoner and …

In the field of binocular stereo matching, remarkable progress has been made by iterative
methods like RAFT-Stereo and CREStereo. However, most of these methods lose …

Abstract Recent cascade Multi-View Stereo (MVS) methods can efficiently estimate high-
resolution depth maps through narrowing hypothesis ranges. However, previous methods …

We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for
high-resolution multi-view stereo. With high computation speed and low memory …

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost
volumes. Due to the high computation and memory consumption of 3D CNN, the resolution …

In this paper, we present a novel recurrent multi-view stereo network based on long short-
term memory (LSTM) with adaptive aggregation, namely AA-RMVSNet. We firstly introduce …