Related papers: Neural Bloom: A Deep Learning Approach to Real-Tim…

We present a neural network-based simulation super-resolution framework that can efficiently and realistically enhance a facial performance produced by a low-cost, realtime physics-based simulation to a level of detail that closely…

We present a new system (NPBG++) for the novel view synthesis (NVS) task that achieves high rendering realism with low scene fitting time. Our method efficiently leverages the multiview observations and the point cloud of a static scene to…

Shadows significantly hinder computer vision tasks in outdoor environments, particularly in field robotics, where varying lighting conditions complicate object detection and localisation. We present FieldNet, a novel deep learning framework…

Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional image enhancement techniques almost impossible to apply. Very…

Recently neural volumetric representations such as neural reflectance fields have been widely applied to faithfully reproduce the appearance of real-world objects and scenes under novel viewpoints and lighting conditions. However, it…

We present a novel Relightable Neural Renderer (RNR) for simultaneous view synthesis and relighting using multi-view image inputs. Existing neural rendering (NR) does not explicitly model the physical rendering process and hence has limited…

Neural implicit representations have been explored to enhance visual SLAM algorithms, especially in providing high-fidelity dense map. Existing methods operate robustly in static scenes but struggle with the disruption caused by moving…

Neural Radiance Fields (NeRFs) have demonstrated prominent performance in novel view synthesis. However, their input heavily relies on image acquisition under normal light conditions, making it challenging to learn accurate scene…

We present a deep neural network for removing undesirable shading features from an unconstrained portrait image, recovering the underlying texture. Our training scheme incorporates three regularization strategies: masked loss, to emphasize…

Real-time hair simulation is a vital component in creating believable virtual avatars, as it provides a sense of immersion and authenticity. The dynamic behavior of hair, such as bouncing or swaying in response to character movements like…

In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods…

We propose Unblur-SLAM, a novel RGB SLAM pipeline for sharp 3D reconstruction from blurred image inputs. In contrast to previous work, our approach is able to handle different types of blur and demonstrates state-of-the-art performance in…

Deepfake detection aims to contrast the spread of deep-generated media that undermines trust in online content. While existing methods focus on large and complex models, the need for real-time detection demands greater efficiency. With this…

Neural implicit representations have recently shown promising progress in dense Simultaneous Localization And Mapping (SLAM). However, existing works have shortcomings in terms of reconstruction quality and real-time performance, mainly due…

This paper studies how to flexibly integrate reconstructed 3D models into practical 3D modeling pipelines such as 3D scene creation and rendering. Due to the technical difficulty, one can only obtain rough 3D models (R3DMs) for most real…

Participating media are a pervasive and intriguing visual effect in virtual environments. Unfortunately, rendering such phenomena in real-time is notoriously difficult due to the computational expense of estimating the volume rendering…

Synthesizing realistic videos of talking faces under custom lighting conditions and viewing angles benefits various downstream applications like video conferencing. However, most existing relighting methods are either time-consuming or…

Recent work on Neural Radiance Fields (NeRF) showed how neural networks can be used to encode complex 3D environments that can be rendered photorealistically from novel viewpoints. Rendering these images is very computationally demanding…

We introduce a neural network-based method to denoise pairs of images taken in quick succession, with and without a flash, in low-light environments. Our goal is to produce a high-quality rendering of the scene that preserves the color and…

Medical imaging plays a vital role in modern diagnostics; however, interpreting high-resolution radiological data remains time-consuming and susceptible to variability among clinicians. Traditional image processing techniques often lack the…