Download presentation
Presentation is loading. Please wait.
1
Using Photographs to Enhance Videos of a Static Scene Pravin Bhat 1, C. Lawrence Zitnick 2, Noah Snavely 1, Aseem Agarwala 3, Maneesh Agrawala 4, Michael Cohen 1,2, Brian Curless 1, Sing Bing Kang 2 EGSR 2007 University of Washington 1, Microsoft Research Redmond 2 University of California 3, Adobe Systems 4
2
An overview of Spacetime Fusion
3
Motivation Low quality video Input Video
4
Motivation Low quality video Reconstructed video Input VideoReconstructed Video
5
Motivation Low quality video Reconstructed video –Reconstructed from photos –Good spatial reconstruction –Bad temporal reconstruction Input VideoReconstructed Video
6
Motivation Spacetime Fusion result Input VideoSpacetime Fusion Result
7
Motivation Spacetime Fusion result –Spatial properties of reconstruction –Temporal properties of input video Input VideoSpacetime Fusion Result
8
Define a 3D gradient field Spacetime Fusion
9
Define a 3D gradient field –Spatial gradients from reconstruction –Temporal gradients from input video Spacetime Fusion
10
Define a 3D gradient field –Spatial gradients from reconstruction –Temporal gradients from input video –Key Idea Temporal gradients defined between motion compensated temporal neighbors Spacetime Fusion
11
Define a 3D gradient field –Spatial gradients from reconstruction –Temporal gradients from input video –Key Idea Temporal gradients defined between motion compensated temporal neighbors Video frame: t Video frame: t - 1 Spacetime Fusion
12
Define a 3D gradient field –Spatial gradients from reconstruction –Temporal gradients from input video –Key Idea Temporal gradients defined between motion compensated temporal neighbors Video frame: t Video frame: t - 1 GtGt G t (x, y, t) = V(x, y, t) - V(x, y, t - 1) Spacetime Fusion
13
Define a 3D gradient field –Spatial gradients from reconstruction –Temporal gradients from input video –Key Idea Temporal gradients defined between motion compensated temporal neighbors Video frame: t Video frame: t - 1 GtGt G t (x, y, t) = V(x, y, t) - V(x - u, y - v, t - 1) Spacetime Fusion
14
Define a 3D gradient field –Spatial gradients from reconstruction –Temporal gradients from input video –Key Idea Temporal gradients defined between motion compensated temporal neighbors Increases compatibility between temporal gradients and spatial gradients Spacetime Fusion
15
Define a 3D gradient field –Spatial gradients from reconstruction –Temporal gradients from input video –Key Idea Temporal gradients defined between motion compensated temporal neighbors Increases compatibility between temporal gradients and spatial gradients Integrate the 3D gradient field Spacetime Fusion
16
Integrating the gradient field Solve linear system: Av = b
17
Integrating the gradient field Solve linear system: Av = b Constraints: v x, y, t – v x-1, y, t = G x (x, y, t) v x, y, t – v x, y-1, t = G y (x, y, t) v x, y, t – v x-u, y-v, t = G t (x, y, t) Spacetime Fusion
18
Applications
19
Enhanced Exposure
20
Input Video Edit Propagation
21
User Edits
22
Edit Propagation User Edits
23
Edit Propagation User Edits
24
Edit Propagation User Edits
25
Edit Propagation User Edits
26
Edit Propagation
27
Edited Video Edit Propagation
28
Super-Resolution
29
Conclusion Spacetime fusion
30
Conclusion Spacetime fusion –Combines spatial and temporal gradients from two different sources
31
Conclusion Spacetime fusion –Combines spatial and temporal gradients from two different sources –Requires motion vectors for temporal source stereo (static scenes) flow (dynamic scenes)
32
Conclusion Spacetime fusion –Combines spatial and temporal gradients from two different sources –Requires motion vectors for temporal source stereo (static scenes) flow (dynamic scenes) –Major applications Enforcing temporal coherence Transferring lighting information
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.