Related papers: Rendering Large Volume Datasets in Unreal Engine 5…

Coding 4K data has become of vital interest in recent years, since the amount of 4K data is significantly increasing. We propose a coding chain with spatial down- and upscaling that combines the next-generation VVC codec with machine…

The tradeoff between reconstruction quality and compute required for video super-resolution (VSR) remains a formidable challenge in its adoption for deployment on resource-constrained edge devices. While transformer-based VSR models have…

Neural fields, also known as implicit neural representations (INRs), have shown a remarkable capability of representing, generating, and manipulating various data types, allowing for continuous data reconstruction at a low memory footprint.…

Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have…

Technological advances for measuring or simulating volume data have led to large data sizes in many research areas such as biology, medicine, physics, and geoscience. Here, large data can refer to individual data sets with high spatial…

Tsetlin machines (TMs) have been successful in several application domains, operating with high efficiency on Boolean representations of the input data. However, Booleanizing complex data structures such as sequences, graphs, images, signal…

The tensor-train (TT) decomposition is widely used to compress large tensors into a more compact form by exploiting their inherent data structures. A fundamental approach for constructing the TT format is the well-known TT-SVD method, which…

Diffusion models have shown great potential in generating realistic image detail. However, adapting these models to video super-resolution (VSR) remains challenging due to their inherent stochasticity and lack of temporal modeling. Previous…

We introduce a learning-based depth map fusion framework that accepts a set of depth and confidence maps generated by a Multi-View Stereo (MVS) algorithm as input and improves them. This is accomplished by integrating volumetric visibility…

In the perception task of autonomous driving, multi-modal methods have become a trend due to the complementary characteristics of LiDAR point clouds and image data. However, the performance of multi-modal methods is usually limited by the…

Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in modeling high-frequency texture details. We introduce VINS-120K, the first large-scale…

The gaming and entertainment industry is rapidly evolving, driven by immersive experiences and the integration of generative AI (GAI) technologies. Training such models effectively requires large-scale datasets that capture the diversity…

Direct volume rendering (DVR) aims to help users identify and examine regions of interest (ROIs) within volumetric data, and feature representations that support effective ROI classification and clustering play a fundamental role in volume…

We propose a neural network-based real-time volume rendering method for realistic and efficient rendering of volumetric media. The traditional volume rendering method uses path tracing to solve the radiation transfer equation, which…

Capturing general deforming scenes from monocular RGB video is crucial for many computer graphics and vision applications. However, current approaches suffer from drawbacks such as struggling with large scene deformations, inaccurate shape…

The exponential growth of video traffic has placed increasing demands on bandwidth and storage infrastructure, particularly for content delivery networks (CDNs) and edge devices. While traditional video codecs like H.264 and HEVC achieve…

In the last few years, deep neural networks opened the doors for big advances in novel view synthesis. Many of these approaches are based on a (coarse) proxy geometry obtained by structure from motion algorithms. Small deficiencies in this…

Vector Symbolic Architectures (VSAs) provide a well-defined algebraic framework for compositional representations in hyperdimensional spaces. We introduce HyperSpace, an open-source framework that decomposes VSA systems into modular…

Recent work on implicit neural representations (INRs) has evidenced their potential for efficiently representing and encoding conventional video content. In this paper we, for the first time, extend their application to immersive…

U-Net architectures are ubiquitous in state-of-the-art deep learning, however their regularisation properties and relationship to wavelets are understudied. In this paper, we formulate a multi-resolution framework which identifies U-Nets as…