# LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregation

arXiv: https://arxiv.org/abs/2406.19833 · HTML: https://mlsanity.com/paper/2406.19833/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 66 references that are in the map.
- First posted on arXiv 28 Jun 2024.

## Builds on (most cited first, 30 of 47)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network](https://mlsanity.com/paper/1703.02719/) (2017)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Learning Depth with Convolutional Spatial Propagation Network](https://mlsanity.com/paper/1810.02695/) (2018)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching](https://mlsanity.com/paper/2007.12140/) (2020)
- [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://mlsanity.com/paper/1909.05845/) (2019)
- [Strip Pooling: Rethinking Spatial Pooling for Scene Parsing](https://mlsanity.com/paper/2003.13328/) (2020)
- [Domain-invariant Stereo Matching Networks](https://mlsanity.com/paper/1911.13287/) (2019)
- [Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching](https://mlsanity.com/paper/2403.00486/) (2024)
- [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://mlsanity.com/paper/1807.08865/) (2018)
- [SegStereo: Exploiting Semantic Information for Disparity Estimation](https://mlsanity.com/paper/1807.11699/) (2018)
- [MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching](https://mlsanity.com/paper/2108.09770/) (2021)

## Built on by (most cited first, 28 of 28)

- [SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models](https://mlsanity.com/paper/2411.13112/) (2024)
- [Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching](https://mlsanity.com/paper/2512.11130/) (2025)
- [BANet: Bilateral Aggregation Network for Mobile Stereo Matching](https://mlsanity.com/paper/2503.03259/) (2025)
- [Light of Normals: Unified Feature Representation for Universal Photometric Stereo](https://mlsanity.com/paper/2506.18882/) (2025)
- [Stereo Any Video: Temporally Consistent Stereo Matching](https://mlsanity.com/paper/2503.05549/) (2025)
- [Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data](https://mlsanity.com/paper/2411.14053/) (2024)
- [Lite Any Stereo: Efficient Zero-Shot Stereo Matching](https://mlsanity.com/paper/2511.16555/) (2025)
- [FastRSR: Efficient and Accurate Road Surface Reconstruction from Bird's Eye View](https://mlsanity.com/paper/2504.09535/) (2025)
- [StereoCarla: A High-Fidelity Driving Dataset for Generalizable Stereo](https://mlsanity.com/paper/2509.12683/) (2025)
- [FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attention](https://mlsanity.com/paper/2509.23733/) (2025)
- [StereoDETR: Stereo-based Transformer for 3D Object Detection](https://mlsanity.com/paper/2511.18788/) (2025)
- [MAFNet:Multi-frequency Adaptive Fusion Network for Real-time Stereo Matching](https://mlsanity.com/paper/2512.04358/) (2025)
- [ThermoStereoRT: Thermal Stereo Matching in Real Time via Knowledge Distillation and Attention-based Refinement](https://mlsanity.com/paper/2504.07418/) (2025)
- [ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving](https://mlsanity.com/paper/2508.13977/) (2025)
- [CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding](https://mlsanity.com/paper/2510.22119/) (2025)
- [RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo](https://mlsanity.com/paper/2511.10107/) (2025)
- [Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI](https://mlsanity.com/paper/2606.22971/) (2026)
- [DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions](https://mlsanity.com/paper/2505.05091/) (2025)
- [Pixel-Optimization-Free Patch Attack on Stereo Depth Estimation](https://mlsanity.com/paper/2506.17632/) (2025)
- [ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching](https://mlsanity.com/paper/2506.21091/) (2025)
- [MatchAttention: Embedding Explicit Matching Constraints into Attention for Efficient Stereo Matching](https://mlsanity.com/paper/2510.14260/) (2025)
- [PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching](https://mlsanity.com/paper/2510.20178/) (2025)
- [Pip-Stereo: Progressive Iterations Pruner for Iterative Optimization based Stereo Matching](https://mlsanity.com/paper/2602.20496/) (2026)
- [Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching](https://mlsanity.com/paper/2606.24457/) (2026)
- [LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching](https://mlsanity.com/paper/2606.25437/) (2026)
- [URS-Stereo: Uncertainty-Guided Residual Search for Real-Time Stereo Matching](https://mlsanity.com/paper/2607.06779/) (2026)
- [TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors](https://mlsanity.com/paper/2607.12571/) (2026)
- [STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching](https://mlsanity.com/paper/2607.19986/) (2026)

## Abstract (arXiv)

We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the matching process. Departing from conventional methodologies that rely on aggregating computationally intensive 4D costs, LightStereo adopts the 3D cost volume as a lightweight alternative. While similar approaches have been explored previously, our breakthrough lies in enhancing performance through a dedicated focus on the channel dimension of the 3D cost volume, where the distribution of matching costs is encapsulated. Our exhaustive exploration has yielded plenty of strategies to amplify the capacity of the pivotal dimension, ensuring both precision and efficiency. We compare the proposed LightStereo with existing state-of-the-art methods across various benchmarks, which demonstrate its superior performance in speed, accuracy, and resource utilization. LightStereo achieves a competitive EPE metric in the SceneFlow datasets while demanding a minimum of only 22 GFLOPs and 17 ms of runtime, and ranks 1st on KITTI 2015 among real-time models. Our comprehensive analysis reveals the effect of 2D cost aggregation for stereo matching, paving the way for real-world applications of efficient stereo systems. Code will be available at https://github.com/XiandaGuo/OpenStereo.