Related papers: Learning Kernel-Modulated Neural Representation fo…

Artificial neural networks have revolutionized fields from computer vision to natural language processing, yet their growing energy and computational demands threaten future progress. Optical neural networks promise greater speed,…

To enhance image compression performance, recent deep neural network-based research can be divided into three categories: a learnable codec, a postprocessing network, and a compact representation network. The learnable codec has been…

Efficient and accurate segmentation of light field is an important task in computer vision and graphics. The large volume of input data and the redundancy of light field make it an open challenge. In the paper, we propose a novel graph…

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt…

Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former…

Light field cameras capture both the spatial and the angular properties of light rays in space. Due to its property, one can compute the depth from light fields in uncontrolled lighting environments, which is a big advantage over active…

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been…

High-energy, large-scale particle colliders in nuclear and high-energy physics generate data at extraordinary rates, reaching up to $1$ terabyte and several petabytes per second, respectively. The development of real-time, high-throughput…

Learning powerful feature representations with CNNs is hard when training data are limited. Pre-training is one way to overcome this, but it requires large datasets sufficiently similar to the target domain. Another option is to design…

We address efficient and structure-aware 3D scene representation from images. Nerflets are our key contribution -- a set of local neural radiance fields that together represent a scene. Each nerflet maintains its own spatial position,…

In recent years, deep generative models have gained significance due to their ability to synthesize natural-looking images with applications ranging from virtual reality to data augmentation for training computer vision models. While…

Existing compression methods typically focus on the removal of signal-level redundancies, while the potential and versatility of decomposing visual data into compact conceptual components still lack further study. To this end, we propose a…

The light transport (LT) of a scene describes how it appears under different lighting and viewing directions, and complete knowledge of a scene's LT enables the synthesis of novel views under arbitrary lighting. In this paper, we focus on…

Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable…

This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions. DCUNet is designed with a…

Deep generative models allow for photorealistic image synthesis at high resolutions. But for many applications, this is not enough: content creation also needs to be controllable. While several recent works investigate how to disentangle…

Novel view synthesis has recently been revolutionized by learning neural radiance fields directly from sparse observations. However, rendering images with this new paradigm is slow due to the fact that an accurate quadrature of the volume…

Implicit neural representations (INRs), which leverage neural networks to represent signals by mapping coordinates to their corresponding attributes, have garnered significant attention. They are extensively utilized for image…

Current methods for extracting intrinsic image components, such as reflectance and shading, primarily rely on statistical priors. These methods focus mainly on simple synthetic scenes and isolated objects and struggle to perform well on…

We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image. Specifically, to encode an image, we fit it with an MLP…