If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.
If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.
Time-slice photography is a popular effect that visualizes the passing of time by aligning and stitching multiple images together into a single image. This paper extends this effect to video using robust video alignment and proposes an easy-to-use system for creating time-slice videos.
Zhaopeng Cui
Simon Fraser University
Oliver Wang
Adobe Research
Ping Tan
Simon Fraser University
Jue Wang
Adobe Research
In this system for editing video of dialogue-driven scenes, the input is a script and multiple video takes, capturing different camera framings or performances of the scene. The system automatically selects a clip from one of the takes for each line of dialogue, based on film-editing idioms.
Mackenzie Leake
Stanford University
Abe Davis
Stanford University
Anh Truong
Adobe Research
Maneesh Agrawala
Stanford University
In this method for automated aerial videography in dynamic and cluttered environments, the algorithm takes high-level plans alongside interactively defined aesthetic framing objectives as input. It includes coordination between multiple drones to enable multi-view shots. The algorithm runs in real time and computes motion plans in milliseconds.
Tobias Naegeli
ETH Zürich
Lukas Meier
ETH Zürich
Alexander Domahidi
embotech GmbH
Javier Alonso Mora
Technische Universiteit Delft
Otmar Hilliges
ETH Zürich
A hybrid imaging system that combines a Lytro camera and a standard video camera. Given a 3-fps light-field sequence and a 30-fps 2D video, the system can generate a full light-field video at 30 fps using convolutional neural networks.
Ting-Chun Wang
University of California, Berkeley
Jun-Yan Zhu
University of California, Berkeley
Nima Khademi Kalantari
University of California, San Diego
Alexei Efros
University of California, Berkeley
Ravi Ramamoorthi
University of California, San Diego