An important line of research attempts to explain CNN image classifier
p...
We present the Cross-stitched Multi-task Unified Dual Recursive Network
...
In this work we introduce a biologically inspired long-range skip connec...
Spherical cameras capture scenes in a holistic manner and have been used...
The task of transforming a furnished room image into a background-only i...
In this work we contribute a distribution shift benchmark for a computer...
A series of 2D (and 3D) keypoint estimation tasks are built upon heatmap...
In this paper, a marker-based, single-person optical motion capture meth...
We introduce HUMAN4D, a large and multimodal 4D dataset that contains a
...
Pano3D is a new benchmark for depth estimation from spherical panoramas....
Spherical 360 video is a novel media format, rapidly becoming adopted
in...
Immersive 3D media is an emerging type of media that captures, encodes a...
It has been shown that global scene understanding tasks like layout
esti...
6D pose estimation is crucial for augmented reality, virtual reality, ro...
In this work we consider UAVs as cooperative agents supporting human use...
Estimating a scene's lighting is a very important task when compositing
...
360^∘ video is a novel media format, rapidly becoming adopted in media
p...
With the advent of consumer grade depth sensors, low-cost volumetric cap...
Machine learning is driven by data, yet while their availability is
cons...
Learning based approaches for depth perception are limited by the
availa...
Omnidirectional vision is becoming increasingly relevant as more efficie...
Multi-view capture systems are complex systems to engineer. They require...
Depth perception is considered an invaluable source of information for
v...
Recent work on depth estimation up to now has only focused on projective...
The latest developments in 3D capturing, processing, and rendering provi...