While image diffusion models have made significant progress in text-driven 3D content
creation they often fail to accurately capture the intended meaning of text prompts especially …

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

3D reconstruction aims to recover the dense 3D structure of a scene. It plays an essential
role in various applications such as Augmented/Virtual Reality (AR/VR), autonomous driving …

Over the years, learning-based multi-view stereo methods have achieved great success
based on their coarse-to-fine depth estimation frameworks. However, 3D CNN-based cost …

Learning surface by neural implicit rendering has been a promising way for multi-view
reconstruction in recent years. Existing neural surface reconstruction methods, such as …

Abstract Unsupervised Multi-View Stereo (MVS) methods have achieved promising progress
recently. However, previous methods primarily depend on the photometric consistency …

State-of-the-art stereo matching networks trained on in-domain data often underperform on
cross-domain scenes. Intuitively, leveraging the zero-shot capacity of a foundation model …

Learning robust local image feature matching is a fundamental low-level vision task, which
has been widely explored in the past few years. Recently, detector-free local feature …

Reconstructing the three-dimensional structure of a scene is a classic and fundamental
problem in computer vision, but it has been revolutionized by recent advancements in deep …

3-D reconstruction is essential to defect localization. This article proposes LCM-MVSNet, a
novel multi-view stereo (MVS) network with learnable cost metric (LCM) for more accurate …