/Stereo-Matching

Stereo matching

Primary LanguagePython

Stereo-Matching

General pipeline: Cost Computation -> Cost Aggregation -> Disparity Optimization -> Disparity Refinement

-

1. Cost Computation:

Census cost = Local binary pattern -> Hamming distance

截圖 2023-01-22 下午4 45 15

2. Cost Aggregation:

Refine the cost according to nearby costs. [Tips] Joint bilateral filter (for the cost of each disparty)

截圖 2023-01-22 下午4 46 40

3. Disparity Optimization:

Determine disparity based on estimated cost. [Tips] Winner-take-all

截圖 2023-01-22 下午4 47 23

4. Disparity Refinement:

Do whatever to enhance the disparity map.[Tips] Left-right consistency check -> Hole filling -> Weighted median filtering

截圖 2023-01-22 下午4 47 48

截圖 2023-01-22 下午4 48 00

截圖 2023-01-22 下午4 48 12

-

Resuls

Tsukuba: bad pixel rate = 4.41%

Tsukuba

Venus: bad pixel rate = 1.52%

Venus

Teddy: bad pixel rate = 9.39%

Teddy

Cones: bad pixel rate = 7.85%

Cones