Recent Papers
-
Perception of Strength and Power of Realistic Male Characters
We investigated the influence of body shape and pose on the perception of physical strength and s...
Show now -
Towards Probabilistic Volumetric Reconstruction using Ray Potentials
This paper presents a novel probabilistic foundation for volumetric 3-d reconstruction. We formul...
Show now -
FlowCap: 2D Human Pose from Optical Flow
We estimate 2D human pose from video using only optical flow. The key insight is that dense optic...
Show now -
Linking Objects to Actions: Encoding of Target Object and Grasping Strategy in Primate Ventral Premotor Cortex
Neural activity in ventral premotor cortex (PMv) has been associated with the process of matching...
Show now -
Discrete Optimization for Optical Flow
We propose to look at large-displacement optical flow from a discrete point of view. Motivated by...
Show now -
Joint 3D Object and Layout Inference from a single RGB-D Image
Inferring 3D objects and the layout of indoor scenes from a single RGB-D image captured with a Ki...
Show now -
Smooth Loops for Unconstrained Video
Converting unconstrained video sequences into videos that loop seamlessly is an extremely challen...
Show now -
Joint 3D Estimation of Vehicles and Scene Flow
Three-dimensional reconstruction of dynamic scenes is an important prerequisite for applications ...
Show now -
Map-Based Probabilistic Visual Self-Localization
Accurate and efficient self-localization is a critical problem for autonomous systems. This paper...
Show now -
Dyna: A Model of Dynamic Human Shape in Motion
To look human, digital full-body avatars need to have soft tissue deformations like those of real...
Show now
Recent Videos
- Towards Probabilistic Volumetric Reconstruction using Ray Potentials
- Object Scene Flow for Autonomous Vehicles
- Displets: Resolving Stereo Ambiguities using Object Knowledge
- Joint 3D Object and Layout Inference from a single RGB-D Image
- Dyna: A Model of Dynamic Human Shape in Motion
- Intrinsic Video
- MoSh: Motion and Shape Capture from Sparse Markers
- Scans to Avatars
- Breathing Life into Shape
- FAUST: Dataset and evaluation for 3D mesh registration
Recent Projects
-
Volumetric Reconstruction
This paper presents a novel probabilistic foundation for volumetric 3-d reconstruction. We ...
Show now -
FlowCap
We estimate 2D human pose from video using only optical flow. The key insight is that dense...
Show now -
Smooth Loops from Unconstrained Video
...
Show now -
From Objects to Actions
In this project we ask how objects are represented for grasping, how this representation ev...
Show now -
PCA Flow
Despite decades of research, a fast optical flow algorithm, that is also accurate, remain...
Show now -
Object Scene Flow
We propose a novel model and dataset for 3D scene flow estimation with an applicatio...
Show now -
Stereo with Displets
Stereo techniques have witnessed tremendous progress over the last decades, yet some...
Show now -
Facade Segmentation
Paper Title: Efficient Facade Segmentation using Auto Context
Show now -
MoSh
Motion and Shape Capture from Sparse Markers While marker-b...
Show now -
Motion Blur in Layers
Videos contain complex spatially-varying motion blur due to the combination of object mot...
Show now
Recent News
-
Ernst-Schoemperlen Prize
Andreas Geiger has been awarded the Ernst-Schoemperlen Prize from the KIT Mobility Systems Center...
Show now -
Tiny Motions Bring Digital Doubles to Life
Researchers at the Max Planck Institute for Intelligent Systems unveil new technology for motion ...
Show now -
Helmholtz Prize
2013 Helmholtz Prize
Show now -
BMVC13 Best Science Paper Award
Committee and authors receiving the prize at the banquet at the Bristol’s Great Council Hall.
Show now -
CVPR13 Best Paper Runner-Up
The awarded authors and committee
Show now -
Like our Facebook page
follow the social side of Perceiving Systems. like our page on Facebook.
Show now -
MPI Sintel Flow
foo bar
Show now -
Visual Orientation and Directional Selectivity Through Thalamic Synchrony
Visual Orientation and Directional Selectivity Through Thalamic Synchrony
Show now -
DRAPE: DRessnig Any PErson
DRAPE: DRessnig Any PErson
Show now -
CVPR 2012
Current object class recognition systems typically target 2D bounding box localization, encourage...
Show now -
CVPR2012
Although facial feature detection from 2D images is a well-studied field, there is a lack of real...
Show now -
Intrinsic
Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance
Show now -
CVPR 2012
From Pictorial Structures to Deformable Structures
Show now -
CVPR 2012
Layered Segmentation and Optical Flow Estimation Over Time
Show now
Recent Talks
- Data-Driven Methods for Video Analysis and Enhancement
- (Irfan Essa, September 10th, 2015 14:00)
- Bayesian Image-Based Rendering and Application to Stereoscopic Cinema and 3DTV
- (Sergi Rocamora, September 8th, 2015 10:00)
- Applying Computer Vision and Graphics Research in Visual Effects and Entertainment
- (Darren Cosker, September 2nd, 2015 10:15)