• Corpus ID: 209386718

Dim the Lights! - Low-Rank Prior Temporal Data for Specular-Free Video Recovery

@article{Alsaleh2019DimTL,
  title={Dim the Lights! - Low-Rank Prior Temporal Data for Specular-Free Video Recovery},
  author={Samar M. Alsaleh and Angelica I. Avil{\'e}s-Rivero and No{\'e}mie Debroux and James K. Hahn},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.07764}
}
The appearance of an object is significantly affected by the illumination conditions in the environment. This is more evident with strong reflective objects as they suffer from more dominant specular reflections, causing information loss and discontinuity in the image domain. In this paper, we present a novel framework for specular-free video recovery with special emphasis on dealing with complex motions coming from objects or camera. Our solution is a twostep approach that allows for both… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 55 REFERENCES
Specularity Removal in Images and Videos: A PDE Approach
TLDR
A unified framework for separating specular and diffuse reflection components in images and videos of textured scenes and an application termed dichromatic editing is presented in which the diffuse and the specular components are processed independently to produce a variety of visual effects.
How Not to Be Seen — Object Removal from Videos of Crowded Scenes
TLDR
This work proposes a new approach to video completion that can deal with complex scenes containing dynamic background and non‐periodical moving objects, and builds upon the idea that the spatio‐temporal hole left by a removed object can be filled with data available on other regions of the video where the occluded objects were visible.
Background Inpainting for Videos with Dynamic Objects and a Free-Moving Camera
TLDR
This work provides experimental validation with several real-world video sequences to demonstrate that, unlike in previous work, inpainting videos shot with free-moving cameras does not necessarily require estimation of absolute camera positions and per-frame per-pixel depth maps.
Video Inpainting With Short-Term Windows: Application to Object Removal and Error Concealment
TLDR
Experiments with several challenging video sequences show that the proposed video inpainting method provides visually pleasing results for object removal, error concealment, and background reconstruction context.
Video inpainting of occluding and occluded objects
TLDR
A basic technique to fill-in missing parts of a video sequence taken from a static camera using an optical-flow based mask and a priority based spatio-temporal synthesis scheme for inpainting the stationary background.
Diffuse-Specular Separation and Depth Recovery from Image Sequences
TLDR
The approach integrates color analysis and multibaseline stereo in a synergistic manner to yield accurate separation and depth, as demonstrated by the results on synthetic and real image sequences.
Motion-consistent video inpainting
TLDR
This work proposes a fast and automatic inpainting technique for high-definition videos which works under many challenging conditions such as a moving camera, a dynamic background or a long lasting occlusion and makes a significant improvement, especially in motion preservation, by incorporating the optical flow in several stages of the algorithm.
Video Inpainting of Complex Scenes
TLDR
An automatic video inpainting algorithm which relies on the optimisation of a global, patch-based functional and requires no segmentation or manual input, and can deal with a wider variety of situations than is handled by previous work.
Space-Time Completion of Video
This paper presents a new framework for the completion of missing information based on local structures. It poses the task of completion as a global optimization problem with a well-defined objective
A novel and effective method for specular detection and removal by tensor voting
TLDR
A novel and effective resolution to separate and remove specular components from a single image by adopting tensor voting to obtain reflectance distribution of an input image is proposed.
...
...