# AANet: Adaptive Aggregation Network for Efficient Stereo Matching

arXiv: https://arxiv.org/abs/2004.09548 · HTML: https://mlsanity.com/paper/2004.09548/

## Key facts

- Cited by 202 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2020.

## Built on by (most cited first, 30 of 202)

- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)
- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching](https://mlsanity.com/paper/2403.00486/) (2024)
- [LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector](https://mlsanity.com/paper/2108.08258/) (2021)
- [Accurate and Efficient Stereo Matching via Attention Concatenation Volume](https://mlsanity.com/paper/2209.12699/) (2022)
- [IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching](https://mlsanity.com/paper/2409.00638/) (2024)
- [High-Resolution Optical Flow from 1D Attention and Correlation](https://mlsanity.com/paper/2104.13918/) (2021)
- [STS: Surround-view Temporal Stereo for Multi-view 3D Detection](https://mlsanity.com/paper/2208.10145/) (2022)
- [DEFOM-Stereo: Depth Foundation Model Based Stereo Matching](https://mlsanity.com/paper/2501.09466/) (2025)
- [Bilateral Grid Learning for Stereo Matching Networks](https://mlsanity.com/paper/2101.01601/) (2021)
- [Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective](https://mlsanity.com/paper/2203.10887/) (2022)
- [Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference](https://mlsanity.com/paper/2211.15969/) (2022)
- [MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions](https://mlsanity.com/paper/2104.13325/) (2021)
- [GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature](https://mlsanity.com/paper/2204.00179/) (2022)
- [Neural Markov Random Field for Stereo Matching](https://mlsanity.com/paper/2403.11193/) (2024)
- [ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks](https://mlsanity.com/paper/2201.02263/) (2022)
- [StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision](https://mlsanity.com/paper/2104.05289/) (2021)
- [Context-Enhanced Stereo Transformer](https://mlsanity.com/paper/2210.11719/) (2022)
- [Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching](https://mlsanity.com/paper/2307.14071/) (2023)
- [Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks](https://mlsanity.com/paper/2112.01011/) (2021)
- [TransFlow: Transformer as Flow Learner](https://mlsanity.com/paper/2304.11523/) (2023)
- [Input-level Inductive Biases for 3D Reconstruction](https://mlsanity.com/paper/2112.03243/) (2021)

## Abstract (arXiv)

Despite the remarkable progress made by learning based stereo matching algorithms, one key challenge remains unsolved. Current state-of-the-art stereo models are mostly based on costly 3D convolutions, the cubic computational complexity and high memory consumption make it quite expensive to deploy in real-world applications. In this paper, we aim at completely replacing the commonly used 3D convolutions to achieve fast inference speed while maintaining comparable accuracy. To this end, we first propose a sparse points based intra-scale cost aggregation method to alleviate the well-known edge-fattening issue at disparity discontinuities. Further, we approximate traditional cross-scale cost aggregation algorithm with neural network layers to handle large textureless regions. Both modules are simple, lightweight, and complementary, leading to an effective and efficient architecture for cost aggregation. With these two modules, we can not only significantly speed up existing top-performing models (e.g., 41× than GC-Net, 4× than PSMNet and 38× than GA-Net), but also improve the performance of fast stereo models (e.g., StereoNet). We also achieve competitive results on Scene Flow and KITTI datasets while running at 62ms, demonstrating the versatility and high efficiency of the proposed method. Our full framework is available at https://github.com/haofeixu/aanet .