ImageBased Motion Blur for Stop Motion Animation

1
Image-Based Motion Blur for Stop Motion Animation

• Gabriel J. Brostow
• Irfan Essa
• SIGGRAPH 01

2
First Stop Motion Animation

• Create a Physical Scene
• Insert Characters / Objects
• Change Scene Slightly
• Record Frame and Repeat

3
Why do we want Motion Blur?

• For fast moving objects
• Prevent time aliasing
• Need for a tool to convey fast motions
• Realistic Perception
• Notice the absence

4
Overview

• Segmentation
• Rigid blob tracking
• Flow Correction
• Rendering Blur
• Results

5
Scene Segmentation

• Grouping the pixels to be tracked
• Ib background image
• If image of current frame
• Im image of moving pixels, where

• Each continuous region of pixels within Im
  is considered to be a blob

6
Pixel Transformations

• Determining frame-by-frame pixel mapping is still
  an on-going research problem
• They use a two-pass approach

One Commercial Method
Their Method
7
Blob Tracking

• Perform similarity search between each blob b in
  Im(i) and Im(i1)
• Reduce search space through assumptions
• Blobs appearance not greatly affected by scale
• Rotation of blob can be determined by absolute
  orientation

8
Blob Tracking (cont.)

• For each b(i), template-match against Im(i1)
  through the normalized cross correlation NCC,
  where
• Interpolate a vector mapping for pixels from
  frame i to i1

9
Flow Correction

• Have an estimate for 2-D transformations by the
  scenes blobs
• Ir(i1) estimate of If(i1) generated by
  applying If(I)s computed vectors
• Ideal 2-D Ir(i1) If(i1), but other effects
• Optical flow finds motion vectors to warp Ir(i1)
  to If(i1)

10
Rendering Blur

• Linearly interpolate pixel paths (L(t))
• User defines shutter speed (S)
• Determine time spent in each cell (w(x,y))

• Distribute pixel (C)

11
Rendering Blur (cont.)

• IAft(ti) Motion of If(ti) from ti to ti S/2
• Get IBef(ti) ti to ti - S/2
• Pixel-wise average these occupancy maps

• Some pixels have few or no pixels move through
  them

12
Results

• Examples
• Representative input and output pair

13
Results

• Examples
• Affects of different shutter speeds

14
Results

• Examples
• Shutter speed vs. interpolation

15
Results

• Examples
• Problems with shadows

16
Fin