# Bi3D: Stereo Depth Estimation via Binary Classifications

arXiv: https://arxiv.org/abs/2005.07274 · HTML: https://mlsanity.com/paper/2005.07274/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2020.

## Built on by (most cited first, 30 of 34)

- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [DynamicStereo: Consistent Dynamic Depth from Stereo Videos](https://mlsanity.com/paper/2305.02296/) (2023)
- [QuadTree Attention for Vision Transformers](https://mlsanity.com/paper/2201.02767/) (2022)
- [MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions](https://mlsanity.com/paper/2104.13325/) (2021)
- [OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline](https://mlsanity.com/paper/2312.00343/) (2023)
- [GEDepth: Ground Embedding for Monocular Depth Estimation](https://mlsanity.com/paper/2309.09975/) (2023)
- [A Decomposition Model for Stereo Matching](https://mlsanity.com/paper/2104.07516/) (2021)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [Binary TTC: A Temporal Geofence for Autonomous Navigation](https://mlsanity.com/paper/2101.04777/) (2021)
- [Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation](https://mlsanity.com/paper/2210.02009/) (2022)
- [TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network](https://mlsanity.com/paper/2211.13755/) (2022)
- [Estimating Image Depth in the Comics Domain](https://mlsanity.com/paper/2110.03575/) (2021)
- [Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context](https://mlsanity.com/paper/2311.17524/) (2023)
- [Cross-spectral Gated-RGB Stereo Depth Estimation](https://mlsanity.com/paper/2405.12759/) (2024)
- [Gated Stereo: Joint Depth Estimation from Gated and Wide-Baseline Active Stereo Cues](https://mlsanity.com/paper/2305.12955/) (2023)
- [Stereo Risk: A Continuous Modeling Approach to Stereo Matching](https://mlsanity.com/paper/2407.03152/) (2024)
- [ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images](https://mlsanity.com/paper/2103.07798/) (2021)
- [Virtual Occlusions Through Implicit Depth](https://mlsanity.com/paper/2305.07014/) (2023)
- [Digging Into Normal Incorporated Stereo Matching](https://mlsanity.com/paper/2402.18171/) (2024)
- [Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition](https://mlsanity.com/paper/2104.02424/) (2021)
- [IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions](https://mlsanity.com/paper/2111.14420/) (2021)
- [DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo](https://mlsanity.com/paper/2212.06626/) (2022)
- [Gated Fields: Learning Scene Reconstruction from Gated Videos](https://mlsanity.com/paper/2405.19819/) (2024)
- [Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation](https://mlsanity.com/paper/2507.11540/) (2025)
- [Towards Continual, Online, Self-Supervised Depth](https://mlsanity.com/paper/2103.00369/) (2021)
- [TSTTC: A Large-Scale Dataset for Time-to-Contact Estimation in Driving Scenarios](https://mlsanity.com/paper/2309.01539/) (2023)
- [Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Maps](https://mlsanity.com/paper/2311.16042/) (2023)
- [Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep](https://mlsanity.com/paper/2401.12001/) (2024)
- [Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks](https://mlsanity.com/paper/2605.08320/) (2026)
- [Generating Superpixels for High-resolution Images with Decoupled Patch Calibration](https://mlsanity.com/paper/2108.08607/) (2021)

## Abstract (arXiv)

Stereo-based depth estimation is a cornerstone of computer vision, with state-of-the-art methods delivering accurate results in real time. For several applications such as autonomous navigation, however, it may be useful to trade accuracy for lower latency. We present Bi3D, a method 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. This property offers a powerful mechanism to balance accuracy and latency. Given a strict time budget, Bi3D can detect objects closer than a given distance in as little as a few milliseconds, or estimate depth with arbitrarily coarse quantization, with complexity linear with the number of quantization levels. Bi3D can also use the allotted quantization levels to get continuous depth, but in a specific depth range. For standard stereo (i.e., continuous depth on the whole range), our method is close to or on par with state-of-the-art, finely tuned stereo methods.