Related papers: Progressive Multi-scale Light Field Networks
In this paper we address the problem of view synthesis from large baseline light fields, by turning a sparse set of input views into a Multi-plane Image (MPI). Because available datasets are scarce, we propose a lightweight network that…
Optical approaches have made great strides towards the goal of high-speed, energy-efficient computing necessary for modern deep learning and AI applications. Read-in and read-out of data, however, limit the overall performance of existing…
We propose a novel framework for representing neural fields on triangle meshes that is multi-resolution across both spatial and frequency domains. Inspired by the Neural Fourier Filter Bank (NFFB), our architecture decomposes the spatial…
Modern machine learning applications require huge artificial networks demanding in computational power and memory. Light-based platforms promise ultra-fast and energy-efficient hardware, which may help in realizing next-generation data…
This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation. The key idea is to first formally separate the foreground…
The transformer architectures, based on self-attention mechanism and convolution-free design, recently found superior performance and booming applications in computer vision. However, the discontinuous patch-wise tokenization process…
Conventional stereoscopic displays suffer from vergence-accommodation conflict and cause visual fatigue. Integral-imaging-based displays resolve the problem by directly projecting the sub-aperture views of a light field into the eyes using…
Neural Radiance Fields (NeRFs) can be dramatically accelerated by spatial grid representations. However, they do not explicitly reason about scale and so introduce aliasing artifacts when reconstructing scenes captured at different camera…
Neural Radiance Fields (NeRF) recently emerged as a new paradigm for object representation from multi-view (MV) images. Yet, it cannot handle multi-scale (MS) images and camera pose estimation errors, which generally is the case with…
This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert…
Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only reason about areas that are visible in the image.…
Neural radiance fields (NeRFs) are able to synthesize realistic novel views from multi-view images captured from distinct positions and perspectives. In NeRF's rendering pipeline, neural networks are used to represent a scene independently…
This paper proposes a neural rendering approach that represents a scene as "compressed light-field tokens (CLiFTs)", retaining rich appearance and geometric information of a scene. CLiFT enables compute-efficient rendering by compressed…
It is suggested that low-light image enhancement realizes one-to-many mapping since we have different definitions of NORMAL-light given application scenarios or users' aesthetic. However, most existing methods ignore subjectivity of the…
The Light Field (LF) deblurring task is a challenging problem as the blur images are caused by different reasons like the camera shake and the object motion. The single image deblurring method is a possible way to solve this problem.…
Light field imaging has recently known a regain of interest due to the availability of practical light field capturing systems that offer a wide range of applications in the field of computer vision. However, capturing high-resolution light…
Neural Radiance Fields (NeRFs) are a powerful representation for modeling a 3D scene as a continuous function. Though NeRF is able to render complex 3D scenes with view-dependent effects, few efforts have been devoted to exploring its…
As aliasing artefacts are highly structural and non-local, many MRI reconstruction networks use pooling to enlarge filter coverage and incorporate global context. However, this inadvertently impedes fine detail recovery as downsampling…
We propose a method to compress full-resolution video sequences with implicit neural representations. Each frame is represented as a neural network that maps coordinate positions to pixel values. We use a separate implicit network to…
Recent advances in Neural Radiance Fields (NeRF) have demonstrated significant potential for representing 3D scene appearances as implicit neural networks, enabling the synthesis of high-fidelity novel views. However, the lengthy training…