Methods › Computer Vision › Stereo Depth Estimation Models › Bi3D
Bi3D
Introduced by Abhishek Badki et al. in Bi3D: Stereo Depth Estimation via Binary Classifications
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 dᵢ 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.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection 10 Mar 2023 · 1 repository · arXiv:2303.05886Syntology ran 1 of 1 samples · 0 unverified
-
Bi3D: Stereo Depth Estimation via Binary Classifications 14 May 2020 · 1 repository · arXiv:2005.07274
Tasks archive 2025-07-28
10 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections