With the increased availability of very high-resolution satellite imagery, terrain based
imaging and participatory sensing, inexpensive platforms, and advanced information and …

Motivated by the limitations of existing multi-view stereo benchmarks, we present a novel
dataset for this task. Towards this goal, we recorded a variety of indoor and outdoor scenes …

Leveraging on the recent developments in convolutional neural networks (CNNs), matching
dense correspondence from a stereo pair has been cast as a learning problem, with …

Autonomous vehicles are expected to play a key role in the future of urban transportation
systems, as they offer potential for additional safety, increased productivity, greater …

Today, visual recognition systems are still rarely employed in robotics applications. Perhaps
one of the main reasons for this is the lack of demanding benchmarks that mimic such …

The limitations of current state-of-the-art methods for single-view depth estimation and
semantic segmentations are closely tied to the property of perspective geometry, that the …

We present an approach for joint inference of 3D scene structure and semantic labeling for
monocular video. Starting with monocular image stream, our framework produces a 3D …

Planar primitives tend to be incorrectly detected or incomplete in complex scenes where
adhesions exist between different objects, resulting in topology errors in the reconstructed …

Existing optical flow methods make generic, spatially homogeneous, assumptions about the
spatial structure of the flow. In reality, optical flow varies across an image depending on …

Road scene segmentation is important in computer vision for different applications such as
autonomous driving and pedestrian detection. Recovering the 3D structure of road scenes …