Related papers: Geometry Reinforced Efficient Attention Tuning Equ…

Stereo matching achieves significant progress with iterative algorithms like RAFT-Stereo and IGEV-Stereo. However, these methods struggle in ill-posed regions with occlusions, textureless, or repetitive patterns, due to a lack of global…

In this paper, we propose CGI-Stereo, a novel neural network architecture that can concurrently achieve real-time performance, competitive accuracy, and strong generalization ability. The core of our CGI-Stereo is a Context and Geometry…

Real-time stereo matching methods primarily focus on enhancing in-domain performance but often overlook the critical importance of generalization in real-world applications. In contrast, recent stereo foundation models leverage monocular…

In the field of remote sensing, the scarcity of stereo-matched and particularly lack of accurate ground truth data often hinders the training of deep neural networks. The use of synthetically generated images as an alternative, alleviates…

Recent advances in optimizing Gaussian Splatting for scene geometry have enabled efficient reconstruction of detailed surfaces from images. However, when input views are sparse, such optimization is prone to overfitting, leading to…

Recent advances in generative adversarial networks (GANs) have shown great potentials in realistic image synthesis whereas most existing works address synthesis realism in either appearance space or geometry space but few in both. This…

Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in matching tasks. However, all-pairs correlations lack non-local geometry knowledge and have difficulties tackling local ambiguities in ill-posed regions. In this…

3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…

Fast stereo based 3D object detectors have made great progress recently. However, they lag far behind high-precision stereo based methods in accuracy. We argue that the main reason is due to the poor geometry-aware feature representation in…

Segment Anything Models (SAMs), known for their exceptional zero-shot segmentation performance, have garnered significant attention in the research community. Nevertheless, their performance drops significantly on severely degraded,…

Stereo matching is a core component in many computer vision and robotics systems. Despite significant advances over the last decade, handling matching ambiguities in ill-posed regions and large disparities remains an open challenge. In this…

Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer…

Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, while allowing the rendering of high-resolution images in real-time. However, leveraging 3D Gaussians for surface reconstruction poses…

End-to-end deep learning methods have advanced stereo vision in recent years and obtained excellent results when the training and test data are similar. However, large datasets of diverse real-world scenes with dense ground truth are…

We introduce a new generative approach for synthesizing 3D geometry and images from single-view collections. Most existing approaches predict volumetric density to render multi-view consistent images. By employing volumetric rendering using…

Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias. Although unsupervised image-to-image translation networks represented by CycleGAN show great potential in dealing with domain gap, it…

Despite their impressive performance in various surgical scene understanding tasks, deep learning-based methods are frequently hindered from deploying to real-world surgical applications for various causes. Particularly, data collection,…

The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produce natural-looking images with…

Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…

As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models…