We present Interactive Neural Video Editing (INVE), a real-time video ed...
Geometric camera calibration is often required for applications that
und...
We introduce 3inGAN, an unconditional 3D generative model trained from 2...
This paper investigates the challenge of extracting highlight moments fr...
Video has become a dominant form of media. However, video editing interf...
Existing depth completion methods are often targeted at a specific spars...
We introduce an approach for selecting objects in neural volumetric 3D
r...
In many recent works, multi-layer perceptions (MLPs) have been shown to ...
We present a method that decomposes, or "unwraps", an input video into a...
We present an algorithm that learns a coarse 3D representation of object...
We present a data-driven approach to automate audio signal processing by...
We introduce CharacterGAN, a generative model that can be trained on onl...
Many compelling video processing effects can be achieved if per-pixel de...
DuctTake is a system designed to enable practical compositing of multipl...
Despite significant progress in monocular depth estimation in the wild,
...
We present a method to perform novel view and time synthesis of dynamic
...
Video frame interpolation, the synthesis of novel views in time, is an
i...
In deep CNN based models for semantic segmentation, high accuracy relies...
Deep generative models have become increasingly effective at producing
r...
We present TDNet, a temporally distributed network designed for fast and...
We present TDNet, a temporally distributed network designed for fast and...
Recently there has been an interest in the potential of learning generat...
We present an algorithm to generate diverse foreground objects and compo...
In this work we ask whether it is possible to create a "universal" detec...
Arnab Ghosh 6:32 PM We propose an interactive GAN-based sketch-to-image
...
Most malicious photo manipulations are created using standard image edit...
We present a fully data-driven method to compute depth from diverse mono...
In this paper, we address the problem of 3D object mesh reconstruction f...
While Generative Adversarial Networks (GANs) have seen huge successes in...
In video production, inserting B-roll is a widely used technique to enri...
360 video provides an immersive experience for viewers, allowing them
to...
We aim to generate high resolution shallow depth-of-field (DoF) images f...
We introduce an approach to convert mono audio recorded by a 360 video c...
Localizing moments in a longer video via natural language queries is a n...
Applying image processing algorithms independently to each frame of a vi...
We address the problem of finding realistic geometric corrections to a
f...
While it is nearly effortless for humans to quickly assess the perceptua...
Many image-to-image translation problems are ambiguous, as a single inpu...
We consider retrieving a specific temporal segment, or moment, from a vi...
Recent advances in deep learning have shown exciting promise in filling ...
Motion blur from camera shake is a major problem in videos captured by
h...