Geographic variance in satellite imagery impacts the ability of machine
...
The process of capturing a well-composed photo is difficult and it takes...
Modern recognition systems require large amounts of supervision to achie...
We present PhySG, an end-to-end inverse rendering pipeline that includes...
We present a new framework for semantic segmentation without annotations...
Reconstructing the shape and appearance of real-world objects using meas...
A painter is free to modify how components of a natural scene are depict...
The fashion sense – meaning the clothing styles people wear – in a
geogr...
A common strategy for improving model robustness is through data
augment...
Deep learning has paved the way for strong recognition systems which are...
Planning in unstructured environments is challenging – it relies on sens...
Image datasets with high-quality pixel-level annotations are valuable fo...
Understanding fashion styles and trends is of great potential interest t...
Material understanding is critical for design, geometric modeling, and
a...
We introduce inverse transport networks as a learning architecture for
i...
Copying an element from a photo and pasting it into a painting is a
chal...
Each day billions of photographs are uploaded to photo-sharing services ...
Understanding shading effects in images is critical for a variety of vis...
This paper introduces a deep-learning approach to photographic style tra...
We propose Deep Feature Interpolation (DFI), a new data-driven baseline ...
We propose a new neural network architecture for solving single-image
an...
It is well known that contextual and multi-scale representations are
imp...
Many tasks in computer vision can be cast as a "label changing" problem,...
Recognizing materials in real-world images is a challenging task. Real-w...