Modern generators render talking-head videos with impressive levels of
p...
Rendering articulated objects while controlling their poses is critical ...
Unsupervised generation of high-quality multi-view-consistent images and...
Recent approaches to render photorealistic views from a limited set of
p...
Deep-learning-based algorithms have led to impressive results in
visual-...
Time-to-contact (TTC), the time for an object to collide with the observ...
Content creation, central to applications such as virtual reality, can b...
Stereo-based depth estimation is a cornerstone of computer vision, with
...
This paper presents a new method to synthesize an image from arbitrary v...
Estimating a mesh from an unordered set of sparse, noisy 3D points is a
...
Despite the long history of image and video stitching research, existing...
Convolutions are the fundamental building block of CNNs. The fact that t...
We present Extreme View Synthesis, a solution for novel view extrapolati...
To date, top-performing optical flow estimation methods only take pairs ...
Scene motion, multiple reflections, and sensor noise introduce artifacts...
Motion blur is a fundamental problem in computer vision as it impacts im...
The reflections caused by common semi-reflectors, such as glass windows,...
Power consumption is a critical factor for the deployment of embedded
co...
Neural networks are becoming central in several areas of computer vision...
Image registration for stack-based HDR photography is challenging. If no...