Research map / Architectures and efficiency / Quantization
Bi3D: Stereo Depth Estimation via Binary Classifications
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Estimate depth using binary closer/farther classifications at selected planes instead of enumerating candidate disparities | Bi3D · Scene Flow, 2 levels | mean IOU: 0.9677 -> 0.9702 | Helped |
| Estimate depth using binary closer/farther classifications at selected planes instead of enumerating candidate disparities | Bi3D · Scene Flow, 4 levels | mean IOU: 0.9350 -> 0.9372 | Helped |
| Estimate depth using binary closer/farther classifications at selected planes instead of enumerating candidate disparities | Bi3D · Scene Flow, 8 levels | mean IOU: 0.8826 -> 0.8909 | Helped |
| Estimate depth using binary closer/farther classifications at selected planes instead of enumerating candidate disparities | Bi3D · Scene Flow, 16 levels | mean IOU: 0.8066 -> 0.8307 | Helped |
| Use Bi3D for continuous stereo depth estimation | Bi3D · Scene Flow | EPE: 0.86 -> 0.73 | Helped |
| Use Bi3D for continuous stereo depth estimation | Bi3D · KITTI 2015, All, all | error (%): 1.74 -> 2.21 | Hurt |
| Run binary depth estimation with one tested plane | Bi3D · Scene Flow | latency: 5.3 ms | Helped |
| Allocate disparity planes to a selected depth interval rather than the full range | Bi3D selective depth · Selected disparity range | depth quality within range | Helped |
Closest papers by meaning
- Single View Stereo Matching (CVPR 2018 · similarity 0.89)
- DEFOM-Stereo: Depth Foundation Model Based Stereo Matching (CVPR 2025 · similarity 0.87)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.86)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.86)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.86)
- MonSter: Marry Monodepth to Stereo Unleashes Power (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.