Related papers: Learn how to Prune Pixels for Multi-view Neural Im…

Recently, a race towards the simplification of deep networks has begun, showing that it is effectively possible to reduce the size of these models with minimal or no performance loss. However, there is a general lack in understanding why…

An explainable, efficient and lightweight method for texture generation, called TGHop (an acronym of Texture Generation PixelHop), is proposed in this work. Although synthesis of visually pleasant texture can be achieved by deep neural…

Neural rendering methods have gained significant attention for their ability to reconstruct 3D scenes from 2D images. The core idea is to take multiple views as input and optimize the reconstructed scene by minimizing the uncertainty in…

We propose to combine recent Convolutional Neural Networks (CNN) models with depth imaging to obtain a reliable and fast multi-person pose estimation algorithm applicable to Human Robot Interaction (HRI) scenarios. Our hypothesis is that…

Model compression techniques reduce the computational load and memory consumption of deep neural networks. After the compression operation, e.g. parameter pruning, the model is normally fine-tuned on the original training dataset to recover…

Model-based deep learning (MBDL) is a powerful methodology for designing deep models to solve imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and…

In view synthesis, a neural radiance field approximates underlying density and radiance fields based on a sparse set of scene pictures. To generate a pixel of a novel view, it marches a ray through the pixel and computes a weighted sum of…

This paper addresses the limitations of neural rendering-based multi-view surface reconstruction methods, which require an additional mesh extraction step that is inconvenient and would produce poor-quality surfaces with mesh aliasing,…

Image inpainting is an effective method to enhance distorted digital images. Different inpainting methods use the information of neighboring pixels to predict the value of missing pixels. Recently deep neural networks have been used to…

The task of extracting intrinsic components, such as reflectance and shading, from neural radiance fields is of growing interest. However, current methods largely focus on synthetic scenes and isolated objects, overlooking the complexities…

Finetuning-free personalized image generation can synthesize customized images without test-time finetuning, attracting wide research interest owing to its high efficiency. Current finetuning-free methods simply adopt a single training…

A variety of pruning methods have been introduced for over-parameterized Recurrent Neural Networks to improve efficiency in terms of power consumption and storage utilization. These advances motivate a new paradigm, termed `hyperpruning',…

We present a deep network to recover pixel values lost to clipping. The clipped area of the image is typically a uniform area of minimum or maximum brightness, losing image detail and color fidelity. The degree to which the clipping is…

We present an approach to enhancing the realism of synthetic images. The images are enhanced by a convolutional network that leverages intermediate representations produced by conventional rendering pipelines. The network is trained via a…

Professional photo editing remains challenging, requiring extensive knowledge of imaging pipelines and significant expertise. While recent deep learning approaches, particularly style transfer methods, have attempted to automate this…

We present an overview and evaluation of a new, systematic approach for generation of highly realistic, annotated synthetic data for training of deep neural networks in computer vision tasks. The main contribution is a procedural world…

Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often…

Augmented Reality (AR) applications necessitates methods of inserting needed objects into scenes captured by cameras in a way that is coherent with the surroundings. Common AR applications require the insertion of predefined 3D objects with…

We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields involves optimizing the representation…

We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates…