相关论文: Leveraging Color Channel Independence for Improved…

Intelligent robots require object-level scene understanding to reason about possible tasks and interactions with the environment. Moreover, many perception tasks such as scene reconstruction, image retrieval, or place recognition can…

Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo. This simulated data does not model many of the important…

Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channels, making them…

Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…

Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional…

Reliable perception is fundamental for safety critical decision making in autonomous driving. Yet, vision based object detector neural networks remain vulnerable to uncertainty arising from issues such as data bias and distributional…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

Light plays a vital role in vision either human or machine vision, the perceived color is always based on the lighting conditions of the surroundings. Researchers are working to enhance the color detection techniques for the application of…

This paper tackles the challenge of colorizing grayscale images. We take a deep convolutional neural network approach, and choose to take the angle of classification, working on a finite set of possible colors. Similarly to a recent paper,…

Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…

A fundamental problem faced by object recognition systems is that objects and their features can appear in different locations, scales and orientations. Current deep learning methods attempt to achieve invariance to local translations via…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

We use large amounts of unlabeled video to learn models for visual tracking without manual human supervision. We leverage the natural temporal coherency of color to create a model that learns to colorize gray-scale videos by copying colors…

This paper presents a comprehensive pipeline for recognizing objects targeted by human pointing gestures using RGB images. As human-robot interaction moves toward more intuitive interfaces, the ability to identify targets of non-verbal…

Understanding the shape of a scene from a single color image is a formidable computer vision task. However, most methods aim to predict the geometry of surfaces that are visible to the camera, which is of limited use when planning paths for…

We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many scene elements naturally appear according to multimodal color…

End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of…

We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision.…

Visual representations are central to the learning and generalization capabilities of robotic manipulation policies. While existing methods rely on global or dense features, such representations often entangle task-relevant and irrelevant…

Deep networks have become very popular over the past few years. The main reason for this widespread use is their excellent ability to learn and predict knowledge in a very easy and efficient way. Convolutional neural networks and…