Learning Spatio-temporal Distortion Models for HDR Video Denoising and Deblurring

1. Additional Results for HDR Reconstruction Using Single Interleaved Exposure

This section shows additional HDR results captured with various exposure times.

2. Temporal super-resolution

This section illustrates temporally created 4 sharp HDR frames using our temporal super-resolution network.

Example Secene 1:

Frame 1 Frame 2 Frame 3 Frame 4

Example Secene 2:

Frame 1 Frame 2 Frame 3 Frame 4

3. Blur Adjustment

This section explains continous adjustment of motion blur for the single HDR frame. There is a continous blur information in high exposure that we cut it into individual sharp frames which emulate certain window of time. Then, blur is achieved by averaging temporally reconstructed those sharp HDR frames. The amount of blur depends on the number of averaged frames which means addition of all frames simulate the exact blur information in high exposure. As a result, objects are blurred naturally along the motion direction in our reconstructions.

Cup Pen Marble Candle

Blur setting:

4. Video

This section demonstrates reconstructed HDR videos captured in dynamic scenes using a synthetic data.

Video 1

5. Video

This section demonstrates reconstructed HDR videos captured in dynamic scenes. Videos are reconstructed with our temporal method using captured images.

Video 1 Video 2 Video 3 Video 4

6. Input Images and Results Figure 1

Dual Sensor Capturing

Low Exposure Medium Exposure High Exposure Kalantari et al. Yan et al. Liu et al. Ours

Conventional Sensor Capturing

Low Exposure Medium Exposure High Exposure Kalantari et al. Yan et al. Liu et al.

7. Input Images and Results Figure 9

Dual Sensor Capturing

Low Exposure Medium Exposure High Exposure Kalantari et al. Yan et al. Liu et al. Ours

Conventional Sensor Capturing

Low Exposure Medium Exposure High Exposure Kalantari et al. Yan et al. Liu et al.