Bi3D

2000년 도입 · 논문 2편에서 사용

Bi3D is a stereo depth estimation framework that estimates depth via a series of binary classifications. Rather than testing if objects are at a particular depth *D*, as existing stereo methods do, it classifies them as being closer or farther than *D*. It takes the stereo pair and a disparity $d\_{i}$ and produces a confidence map, which can be thresholded to yield the binary segmentation. To estimate depth on $N + 1$ quantization levels we run this network $N$ times and maximize the probability in Equation 8 (see paper). To estimate continuous depth, whether full or selective, we run the SegNet block of Bi3DNet for each disparity level and work directly on the confidence volume.

출처: Bi3D: Stereo Depth Estimation via Binary Classifications

소개 논문: Bi3D: Stereo Depth Estimation via Binary Classifications