Related papers: Learning-Based View Synthesis for Light Field Came…
Deep Neural Network (DNN)-based image reconstruction, despite many successes, often exhibits uneven fidelity between high and low spatial frequency bands. In this paper we propose the Learning Synthesis by DNN (LS-DNN) approach where two…
Light field presents a rich way to represent the 3D world by capturing the spatio-angular dimensions of the visual signal. However, the popular way of capturing light field (LF) via a plenoptic camera presents spatio-angular resolution…
The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity. However, results of current approaches still fall short of their promise of high-resolution…
Ensuring robustness in face recognition systems across various challenging conditions is crucial for their versatility. State-of-the-art methods often incorporate additional information, such as depth, thermal, or angular data, to enhance…
Recovering 3D geometry of underwater scenes is challenging because of non-linear refraction of light at the water-air interface caused by the camera housing. We present a light field-based approach that leverages properties of angular…
Recent advances in imitation learning have shown significant promise for robotic control and embodied intelligence. However, achieving robust generalization across diverse mounted camera observations remains a critical challenge. In this…
The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs. This is particularly hard in the context of dynamic scenes or…
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…
Learning radiance fields has shown remarkable results for novel view synthesis. The learning procedure usually costs lots of time, which motivates the latest methods to speed up the learning procedure by learning without neural networks or…
3D reconstruction of a scene from Synthetic Aperture Radar (SAR) images mainly relies on interferometric measurements, which involve strict constraints on the acquisition process. These last years, progress in deep learning has…
True video understanding requires making sense of non-lambertian scenes where the color of light arriving at the camera sensor encodes information about not just the last object it collided with, but about multiple mediums -- colored…
Images taken under low-light conditions tend to suffer from poor visibility, which can decrease image quality and even reduce the performance of the downstream tasks. It is hard for a CNN-based method to learn generalized features that can…
Digital imaging systems have traditionally relied on brute-force measurement and processing of pixels arranged on regular grids. In contrast, the human visual system performs significant data reduction from the large number of…
Light field, as a new data representation format in multimedia, has the ability to capture both intensity and direction of light rays. However, the additional angular information also brings a large volume of data. Classical coding methods…
Novel view synthesis from an in-the-wild video is difficult due to challenges like scene dynamics and lack of parallax. While existing methods have shown promising results with implicit neural radiance fields, they are slow to train and…
Given just a few glimpses of a scene, can you imagine the movie playing out as the camera glides through it? That's the lens we take on \emph{sparse-input novel view synthesis}, not only as filling spatial gaps between widely spaced views,…
We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint. Rather than operating over mesh-based structures, our…
We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements, with the goal of synthesizing realistic LiDAR scans from novel viewpoints. NFL combines the rendering power of…
Novel view synthesis in 360$^\circ$ scenes from extremely sparse input views is essential for applications like virtual reality and augmented reality. This paper presents a novel framework for novel view synthesis in extremely sparse-view…
Learning interpretable and interpolatable latent representations has been an emerging research direction, allowing researchers to understand and utilize the derived latent space for further applications such as visual synthesis or…