Related papers: OccCasNet: Occlusion-aware Cascade Cost Volume for…

Neural networks have shown great success in extracting geometric information from color images. Especially, monocular depth estimation networks are increasingly reliable in real-world scenes. In this work we investigate the applicability of…

Large occlusions result in a significant decline in image classification accuracy. During inference, diverse types of unseen occlusions introduce out-of-distribution data to the classification model, leading to accuracy dropping as low as…

Existing state-of-the-art disparity estimation works mostly leverage the 4D concatenation volume and construct a very deep 3D convolution neural network (CNN) for disparity regression, which is inefficient due to the high memory consumption…

Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascade, a training-free sparse attention method that leverages known observations…

We propose a novel stereo-confidence that can be measured externally to various stereo-matching networks, offering an alternative input modality choice of the cost volume for learning-based approaches, especially in safety-critical systems.…

Multiview stereo aims to reconstruct scene depth from images acquired by a camera under arbitrary motion. Recent methods address this problem through deep learning, which can utilize semantic cues to deal with challenges such as textureless…

Occlusion relationship reasoning demands closed contour to express the object, and orientation of each contour pixel to describe the order relationship between objects. Current CNN-based methods neglect two critical issues of the task: (1)…

The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception. Instead of directly fusing estimated depths across LiDAR and stereo…

The performance of monocular depth estimation generally depends on the amount of parameters and computational cost. It leads to a large accuracy contrast between light-weight networks and heavy-weight networks, which limits their…

We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision. We optimize point positions, depths, and weights…

Classification of partially occluded images is a highly challenging computer vision problem even for the cutting edge deep learning technologies. To achieve a robust image classification for occluded images, this paper proposes a novel…

Remote patient monitoring has emerged as a prominent non-invasive method, using digital technologies and computer vision (CV) to replace traditional invasive monitoring. While neonatal and pediatric departments embrace this approach,…

Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do…

Autonomous aerial scanning of target structures is crucial for practical applications, requiring online adaptation to unknown obstacles during flight. Existing methods largely emphasize collision avoidance and efficiency, but overlook…

A Multistage Full Matching disparity estimation scheme (MFM) is proposed in this work. We demonstrate that decouple all similarity scores directly from the low-resolution 4D volume step by step instead of estimating low-resolution 3D cost…

Million-level token inputs in long-context tasks pose significant computational and memory challenges for Large Language Models (LLMs). Recently, DeepSeek-OCR conducted research into the feasibility of Contexts Optical Compression and…

Depth cues have been proved very useful in various computer vision and robotic tasks. This paper addresses the problem of monocular depth estimation from a single still image. Inspired by the effectiveness of recent works on multi-scale…

Recent advances in monocular 3D detection leverage a depth estimation network explicitly as an intermediate stage of the 3D detection network. Depth map approaches yield more accurate depth to objects than other methods thanks to the depth…

Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios. In this paper, we develop a new…

Depth sensing is a critical function for robotic tasks such as localization, mapping and obstacle detection. There has been a significant and growing interest in depth estimation from a single RGB image, due to the relatively low cost and…