Related papers: IGEV++: Iterative Multi-range Geometry Encoding Vo…

Matching cost aggregation plays a fundamental role in learning-based multi-view stereo networks. However, directly aggregating adjacent costs can lead to suboptimal results due to local geometric inconsistency. Related methods either seek…

With the development of deep learning, ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot ability. However, due to the limitations of ViTs in handling resolution sensitivity and…

Currently, single image inpainting has achieved promising results based on deep convolutional neural networks. However, inpainting on stereo images with missing regions has not been explored thoroughly, which is also a significant but…

This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not…

GigaMVS presents several challenges to existing Multi-View Stereo (MVS) algorithms for its large scale, complex occlusions, and gigapixel images. To address these problems, we first apply one of the state-of-the-art learning-based MVS…

Our goal here is threefold: [1] To present a new dense-stereo matching algorithm, tMGM, that by combining the hierarchical logic of tSGM with the support structure of MGM achieves 6-8\% performance improvement over the baseline SGM (these…

Driven by the advancement of 3D devices, stereo vision tasks including stereo matching and stereo conversion have emerged as a critical research frontier. Contemporary stereo vision backbones typically rely on either monocular depth…

In this paper, we propose a novel end-to-end deep neural network model for omnidirectional depth estimation from a wide-baseline multi-view stereo setup. The images captured with ultra wide field-of-view (FOV) cameras on an omnidirectional…

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 of output depth is often considerably limited. Different from…

Tracking objects in 3D space and predicting their 6DoF pose is an essential task in computer vision. State-of-the-art approaches often rely on object texture to tackle this problem. However, while they achieve impressive results, many…

Recent methods in stereo matching have continuously improved the accuracy using deep models. This gain, however, is attained with a high increase in computation cost, such that the network may not fit even on a moderate GPU. This issue…

Real-world applications of stereo matching, such as autonomous driving, place stringent demands on both safety and accuracy. However, learning-based stereo matching methods inherently suffer from the loss of geometric structures in certain…

Traditional multi-view stereo (MVS) methods rely heavily on photometric and geometric consistency constraints, but newer machine learning-based MVS methods check geometric consistency across multiple source views only as a post-processing…

We present Uncertainty-aware Cascaded Stereo Network (UCS-Net) for 3D reconstruction from multiple RGB images. Multi-view stereo (MVS) aims to reconstruct fine-grained scene geometry from multi-view images. Previous learning-based MVS…

With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress. However, it remains a great challenge to accurately extract disparities from real-world image pairs taken by…

In this paper, we propose an efficient multi-scale geometric consistency guided multi-view stereo method for accurate and complete depth map estimation. We first present our basic multi-view stereo method with Adaptive Checkerboard sampling…

Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In…

We propose an online multi-view depth prediction approach on posed video streams, where the scene geometry information computed in the previous time steps is propagated to the current time step in an efficient and geometrically plausible…

Parallel accelerators, such as GPUs, are key enablers for large-scale Machine Learning (ML) applications. However, ML model developers often lack detailed knowledge of the underlying system architectures, while system programmers usually do…

Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing…