The predicted disparity will be evaluated on the pixels in the rectified view of the left event camera.
Prediction Timestamps and Image Indices
The evaluation script evaluates the submission at specific timestamps that correspond to image timestamps at a 1 Hz rate.
These timestamps and corresponding image file indices are specified in the following zip file, also available on the download page: test_disparity_timestamps.zip
The zip file contains
- timestamps in microseconds and
- indices corresponding to the image file names for each sequence, which define the timestamps of the expected disparity predictions for the submission.
While the indices are redundant information with respect to the provided timestamps, they can be used
- to directly associate timestamps to image files.
- to name the predicted disparity files for the submission.
Upload a zip file with exactly the following content:
. ├── interlaken_00_a │ ├── 000020.png │ ├── 000040.png │ ├── ... │ └── 001140.png ├── interlaken_00_b │ └── ... ├── interlaken_01_a │ └── ... ├── thun_01_a │ └── ... ├── thun_01_b │ └── ... ├── zurich_city_12_a │ └── ... ├── zurich_city_13_a │ └── ... ├── zurich_city_13_b │ └── ... ├── zurich_city_14_a │ └── ... ├── zurich_city_14_b │ └── ... ├── zurich_city_14_c │ └── ... └── zurich_city_15_a └── ...
- Each directory contains the same number of png files as the number of timestamps specified in the corresponding csv file.
- The filenames should be of the form xxxxxx.png where xxxxxx consists of the file index filled with ASCII ‘0’ (zero) digits from the left to contain 6 digits. For example, the index 80 would correspond to the filename 000080.png (e.g.
'80'.zfill(6) + '.png'in Python). This naming is not strictly enforced but highly recommended. Internally, the evaluation script sorts the filenames within a directory based on the lexicographical order of the ASCII encoding (e.g.
sorted(glob(...))). The submitted files are then evaluated in that order with the ground truth. The correct order is guaranteed with the suggested naming convention.
Disparity PNG Format
The disparity format must be identical to the one provided in the dataset:
Disparity maps must be saved as 16-bit grayscale/single-channel PNG files. Each pixel I[y,x] contains the value of the disparity multiplied by 256:
I[y,x] = (uint16)(disp[y,x] * 256)
Verification of the Submitted Format
We provide a script on GitHub to verify whether the submission format is correct.