Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
ACM SIGGRAPH 2003 Papers
Interactive digital photomontage
ACM SIGGRAPH 2004 Papers
Recovering Intrinsic Images from a Single Image
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Removal of Shadows from Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
ACM SIGGRAPH 2006 Papers
Two-scale tone management for photographic look
ACM SIGGRAPH 2006 Papers
Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations (Applied Mathematical Sciences)
ACM SIGGRAPH 2007 papers
Scene completion using millions of photographs
ACM SIGGRAPH 2007 papers
Visual equivalence: towards a new standard for image fidelity
ACM SIGGRAPH 2007 papers
The influence of shape on the perception of material reflectance
ACM SIGGRAPH 2007 papers
Efficient gradient-domain compositing using quadtrees
ACM SIGGRAPH 2007 papers
Perception of complex aggregates
ACM SIGGRAPH 2008 papers
Edge-preserving decompositions for multi-scale tone and detail manipulation
ACM SIGGRAPH 2008 papers
Coordinates for instant image cloning
ACM SIGGRAPH 2009 papers
Entropy Minimization for Shadow Removal
International Journal of Computer Vision
GradientShop: A gradient-domain optimization framework for image and video filtering
ACM Transactions on Graphics (TOG)
IEEE Transactions on Pattern Analysis and Machine Intelligence
What is the range of surface reconstructions from a gradient field?
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Covariant derivatives and vision
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Image quality assessment: from error visibility to structural similarity
IEEE Transactions on Image Processing
An interactive perceptual rendering pipeline using contrast and spatial masking
EGSR'07 Proceedings of the 18th Eurographics conference on Rendering Techniques
Temporally consistent gradient domain video editing
EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
MIRAGE'11 Proceedings of the 5th international conference on Computer vision/computer graphics collaboration techniques
Natural image composition with inhomogeneous boundaries
PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part II
Understanding and improving the realism of image composites
ACM Transactions on Graphics (TOG) - SIGGRAPH 2012 Conference Proceedings
Fast adaptive edge-aware mask generation
Proceedings of Graphics Interface 2012
Digital Camouflage Images Using Two-scale Decomposition
Computer Graphics Forum
Object detection, shape recovery, and 3D modelling by depth-encoded hough voting
Computer Vision and Image Understanding
Special Section on CAD/Graphics 2013: Image compositing using dominant patch transformations
Computers and Graphics
Hi-index | 0.00 |
Gradient-domain compositing is an essential tool in computer vision and its applications, e.g., seamless cloning, panorama stitching, shadow removal, scene completion and reshuffling. While easy to implement, these gradient-domain techniques often generate bleeding artifacts where the composited image regions do not match. One option is to modify the region boundary to minimize such mismatches. However, this option may not always be sufficient or applicable, e.g., the user or algorithm may not allow the selection to be altered. We propose a new approach to gradient-domain compositing that is robust to inaccuracies and prevents color bleeding without changing the boundary location. Our approach improves standard gradient-domain compositing in two ways. First, we define the boundary gradients such that the produced gradient field is nearly integrable. Second, we control the integration process to concentrate residuals where they are less conspicuous. We show that our approach can be formulated as a standard least-squares problem that can be solved with a sparse linear system akin to the classical Poisson equation. We demonstrate results on a variety of scenes. The visual quality and run-time complexity compares favorably to other approaches.