CVOct 20, 2022

Multi-View Guided Multi-View Stereo

arXiv:2210.11467v16 citationsh-index: 43
Originality Incremental advance
AI Analysis

This work addresses 3D reconstruction for computer vision applications, but it is incremental as it builds on existing deep multi-view stereo networks.

The paper tackles dense 3D reconstruction from multiple images by using sparse depth measurements to guide deep multi-view stereo networks, resulting in more accurate depth maps as demonstrated on BlendedMVG and DTU datasets.

This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition. Given a deep multi-view stereo network, our framework uses sparse depth hints to guide the neural network by modulating the plane-sweep cost volume built during the forward step, enabling us to infer constantly much more accurate depth maps. Moreover, since multiple viewpoints can provide additional depth measurements, we propose a multi-view guidance strategy that increases the density of the sparse points used to guide the network, thus leading to even more accurate results. We evaluate our Multi-View Guided framework within a variety of state-of-the-art deep multi-view stereo networks, demonstrating its effectiveness at improving the results achieved by each of them on BlendedMVG and DTU datasets.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes