Related papers: SegStereo: Exploiting Semantic Information for Dis…
Disparity estimation is a difficult problem in stereo vision because the correspondence technique fails in images with textureless and repetitive regions. Recent body of work using deep convolutional neural networks (CNN) overcomes this…
Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large…
With the rapid evolution of autonomous driving technology and intelligent transportation systems, semantic segmentation has become increasingly critical. Precise interpretation and analysis of real-world environments are indispensable for…
Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learning frameworks as…
Stereo matching is one of the longest-standing problems in computer vision with close to 40 years of studies and research. Throughout the years the paradigm has shifted from local, pixel-level decision to various forms of discrete and…
Semantic image segmentation is one of fastest growing areas in computer vision with a variety of applications. In many areas, such as robotics and autonomous vehicles, semantic image segmentation is crucial, since it provides the necessary…
In stereo vision, self-similar or bland regions can make it difficult to match patches between two images. Active stereo-based methods mitigate this problem by projecting a pseudo-random pattern on the scene so that each patch of an image…
We revisit the problem of visual depth estimation in the context of autonomous vehicles. Despite the progress on monocular depth estimation in recent years, we show that the gap between monocular and stereo depth accuracy remains large$-$a…
When given two similar images, humans identify their differences by comparing the appearance (e.g., color, texture) with the help of semantics (e.g., objects, relations). However, mainstream binary change detection models adopt a supervised…
This work presents dense stereo reconstruction using high-resolution images for infrastructure inspections. The state-of-the-art stereo reconstruction methods, both learning and non-learning ones, consume too much computational resource on…
The advent of deep learning has brought an impressive advance to monocular depth estimation, e.g., supervised monocular depth estimation has been thoroughly investigated. However, the large amount of the RGB-to-depth dataset may not be…
Video semantic segmentation aims to generate accurate semantic maps for each video frame. To this end, many works dedicate to integrate diverse information from consecutive frames to enhance the features for prediction, where a feature…
Vision and language tasks such as Visual Relation Detection and Visual Question Answering benefit from semantic features that afford proper grounding of language. The 3D depth of objects depicted in 2D images is one such feature. However it…
Semantic communication has emerged as a promising approach for improving efficient transmission in the next generation of wireless networks. Inspired by the success of semantic communication in different areas, we aim to provide a new…
Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…
Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…
Deep supervised hashing has emerged as an influential solution to large-scale semantic image retrieval problems in computer vision. In the light of recent progress, convolutional neural network based hashing methods typically seek pair-wise…
The importance and demands of visual scene understanding have been steadily increasing along with the active development of autonomous systems. Consequently, there has been a large amount of research dedicated to semantic segmentation and…
Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing. CNNs led to considerable improvements in this field, and recent trends replaced the need for ground-truth labels with…
Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition. However, a resulting…