Related papers: Computer Vision and Deep Learning for 4D Augmented…
With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as…
True video understanding requires making sense of non-lambertian scenes where the color of light arriving at the camera sensor encodes information about not just the last object it collided with, but about multiple mediums -- colored…
The semantic segmentation of 3D shapes with a high-density of vertices could be impractical due to large memory requirements. To make this problem computationally tractable, we propose a neural-network based approach that produces 3D…
Machine learning techniques for more efficient video compression and video enhancement have been developed thanks to breakthroughs in deep learning. The new techniques, considered as an advanced form of Artificial Intelligence (AI), bring…
For computer vision systems to operate in dynamic situations, they need to be able to represent and reason about object permanence. We introduce a framework for learning to estimate 4D visual representations from monocular RGB-D, which is…
Omnidirectional (360-degree) video is rapidly gaining popularity due to advancements in immersive technologies like virtual reality (VR) and extended reality (XR). However, real-time streaming of such videos, especially in live mobile…
Neural rendering is a new image and video generation method based on deep learning. It combines the deep learning model with the physical knowledge of computer graphics, to obtain a controllable and realistic scene model, and realize the…
For the problem of 3D object recognition, researchers using deep learning methods have developed several very different input representations, including "multi-view" snapshots taken from discrete viewpoints around an object, as well as…
A recent strand of work in view synthesis uses deep learning to generate multiplane images (a camera-centric, layered 3D representation) given two or more input images at known viewpoints. We apply this representation to single-view view…
Implicit surface representations, such as signed-distance functions, combined with deep learning have led to impressive models which can represent detailed shapes of objects with arbitrary topology. Since a continuous function is learned,…
Recent developments in Multimodal Large Language Models (MLLMs) have significantly improved Vision-Language (VL) reasoning in 2D domains. However, extending these capabilities to 3D scene understanding remains a major challenge. Existing 3D…
Modern deep learning developments create new opportunities for 3D mapping technology, scene reconstruction pipelines, and virtual reality development. Despite advances in 3D deep learning technology, direct training of deep learning models…
Deep learning is an established framework for learning hierarchical data representations. While compute power is in abundance, one of the main challenges in applying this framework to robotic grasping has been obtaining the amount of data…
Recent advances in imitation learning have shown significant promise for robotic control and embodied intelligence. However, achieving robust generalization across diverse mounted camera observations remains a critical challenge. In this…
The recent phenomenal interest in convolutional neural networks (CNNs) must have made it inevitable for the super-resolution (SR) community to explore its potential. The response has been immense and in the last three years, since the…
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem…
Implicit neural representations (INR) have gained increasing attention in representing 3D scenes and images, and have been recently applied to encode videos (e.g., NeRV, E-NeRV). While achieving promising results, existing INR-based methods…
Modern-day display systems demand high-quality rendering. However, rendering at higher resolution requires a large number of data samples and is computationally expensive. Recent advances in deep learning-based image and video…
In the current golden age of multimedia, human visualization is no longer the single main target, with the final consumer often being a machine which performs some processing or computer vision tasks. In both cases, deep learning plays a…
Deep learning with Convolutional Neural Networks has shown great promise in various areas of image-based classification and enhancement but is often unsuitable for predictive modeling involving non-image based features or features without…