Pip-Stereo: Progressive Iterations Pruner for Iterative Optimization based Stereo Matching

Jintu Zheng; Qizhe Liu; HuangXin Xu; Zhuojie Chen

cs.CVFeb 24, 2026

Pip-Stereo: Progressive Iterations Pruner for Iterative Optimization based Stereo Matching

Authors: Jintu Zheng, Qizhe Liu, HuangXin Xu, Zhuojie Chen

Organizations: ARIDGE XPENG

Abstract

While iterative stereo matching achieves high accuracy, its dependence on Recurrent Neural Networks (RNN) hinders edge deployment, a challenge underexplored in existing researches. We analyze iterative refinement and reveal that disparity updates are spatially sparse and temporally redundant. First, we introduce a progressive iteration pruning strategy that suppresses redundant update steps, effectively collapsing the recursive computation into a near-single-pass inference. Second, we propose a collaborative monocular prior transfer framework that implicitly embeds depth priors without requiring a dedicated monocular encoder, thereby eliminating its associated computational burden. Third, we develop FlashGRU, a hardware-aware RNN operator leveraging structured sparsity and I/O-conscious design, achieving a 7.28 $\times$ speedup, 76.6% memory peak reduction and 80.9% global memory requests reduction over natvie ConvGRUs under 2K resolution. Our PipStereo enables real-time, high-fidelity stereo matching on edge hardware: it processes 320 $\times$ 640 frames in just 75ms on an NVIDIA Jetson Orin NX (FP16) and 19ms on RTX 4090, matching the accuracy of large iterative based models, and our generalization ability and accuracy far exceeds that of existing real-time methods. Our embedded AI projects will be updated at: https://github.com/XPENG-Aridge-AI.

Figures & tables

Figure 1: Iteration update positions and hit ratios on Middlebury [ 19 ] test set. Red pixels denote updates; left color bars show consistency with the previous iteration. Refinements are sparse, highly redundant, and affect only a small fraction of the image.

Figure 2: Overview of two-stage training: (1) depth prior transfer via multi-level and cost volume feature alignment, and (2) pruned finetuning with progressively fewer iterations, training only the ConvGRU modules.

Figure 3: Illustrion of the FlashGRU in 2 resolution levels and T loops, with 70% sparisity.

Method	Iters.	Sceneflow [ 16 ]	ETH3D [ 21 ]			KITTI 2012 [ 18 ]				KITTI 2015 [ 8 ]				Latency(s)
		EPE	Bad-1	Bad-1	RMSE	Out-2	Out-2	Out-3	Out-3	D1-bg	D1-all	D1-bg	D1-all
		All	Noc	All	Noc	Noc	All	Noc	All	Noc	Noc	All	All
RaftStereo [ 15 ]	32	0.72	2.44	2.60	0.36	1.92	2.42	1.30	1.66	1.44	1.69	1.58	1.82	2.95
IGEV [ 33 ]	12	0.49	1.12	1.51	0.34	1.71	2.17	1.12	1.44	1.27	1.49	1.38	1.59	1.29
SelectiveIGEV [ 28 ]	12	0.44	1.23	1.56	0.29	1.59	2.05	1.07	1.38	1.22	1.44	1.33	1.55	1.61
DEFOMStereo [ 12 ]	32	0.42	0.70	0.78	0.22	1.43	1.79	0.94	1.18	1.25	1.41	1.15	1.33	5.05

Table 1: In-domain comparison with PipStereo. Top panel lists high-accuracy iterative approaches, while bottom panel includes real-time methods. PipStereo achieves accuracy competitive with state-of-the-art iterative methods while significantly outperforming all high-accuracy approaches in inference latency, and substantially surpassing existing real-time methods in accuracy. The item and item are the best and second best in each panel. Latencies are tested in

384\times 1344

resolution on Orin NX (25W power mode, FP32 precision).

Method	Iter. based	Sunny	Cloudy	Rainy	Foggy	Avg.	Latency(s)
ZeroStereo [ 29 ]	✗	3.15	2.69	11.71	1.70	4.81	OOM
Nerf-Stereo [ 24 ]	✗	2.88	2.95	8.47	3.41	4.43	-
SMoEStereo [ 30 ]	✗	3.51	3.11	6.08	4.77	4.37	-
IGEV [ 33 ]	✓	5.30	5.48	15.41	5.01	7.80	1.29
Selective-IGEV [ 28 ]	✓	5.67	5.35	13.84	4.79	7.41	1.61
DefomStereo [ 12 ]	✓	3.39	3.13	12.84	2.57	5.48	5.05

Table 2: Zero-shot generalization performance. Evaluation on DrivingStereo [ 38 ] under diverse weather conditions, reported using the D1-All metric.

Figure 4: Visual comparison. Leveraging depth prior, PipStereo successfully handles ill-posed regions and produces sharper details and more coherent structures compared to IGEV [ 33 ] .

ID	Method	Alias	Infer iters.	SceneFlow [ 16 ]	Latency(s)
1	Selective-IGEV [ 28 ]	-	12	0.44	1.61
2	-	-	32	0.44	3.57
3	-	-	1	0.64	0.60
4	+MPT (w./o. search)	-	32	0.40	3.40
5	+MPT	PipStereo-i32	1	0.56	0.44
6	+MPT	PipStereo-i32	32	0.38	3.40

Table 3: Integration ablations. MPT substantially boosts performance; PIP effectively curbs accuracy degradation from fewer iterations, while FlashGRU provides acceleration for methods that more than one iteration under PIP.

Flash.	Size	RNN Latency	Mem. Peak (MiB)	Mem. Request
✗	320 $\times$ 736	28.8ms	743	2.260 $\times e^{6}$
✓	320 $\times$ 736	14.8ms ( $\times$ 1.94 )	561 ( $\downarrow$ 24.4% )	$\bm{0.947\times e^{6}}$ ( $\downarrow$ 58.1% )
✗	640 $\times$ 1472	45.2ms	1431	9.258 $\times e^{6}$
✓	640 $\times$ 1472	15.2ms ( $\times$ 2.97 )	715 ( $\downarrow$ 50.0% )	$\bm{2.189\times e^{6}}$ ( $\downarrow$ 76.4% )
✗	1280 $\times$ 2944	122.4ms	4105	37.756 $\times e^{6}$
✓	1280 $\times$ 2944	16.8ms ( $\times$ 7.28 )	957 ( $\downarrow$ 76.6% )	$\bm{7.224\times e^{6}}$ ( $\downarrow$ 80.9% )

Table 4: Efficiency gain of P3-Flash on NVIDIA RTX4090 24GB (Ada Lovelace). Baseline without ”Flash” is the ConvGRU implementation of Selective-IGEV [ 28 ] , and tested on downsampled 4

\times

feature map for update block. Red marks the speedup ratio. Green marks the reduction ratio. The ”Request” is the sum of ”ld/st” micro requests to GPU global memory.

Stereo Matching

Stereo matching estimates depth by finding corresponding points in paired images and measuring their disparity.

See all 56 papers

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts
Mar 2, 2026Xianqi Wang, Hao Yang, Hangtian Wang +4Stereo Matching Visual Prompt Learning
Huazhong University of Science and Technology · Optics Valley Laboratory
WAVE-Stereo: Warp-Aligned Volume Encoding for Stereo Matching
Jul 15, 2026Zehan Liu, Yage He, Xianwu GongStereo Matching Stereo Depth Estimation
School of Electronics and Control Engineering Chang’an University Xi’an, China
MatchAttention: Embedding Explicit Matching Constraints into Attention for Efficient Stereo Matching
Oct 16, 2025Tingman Yan, Tao Liu, Chenghao Li +4Image Matching Stereo Matching
School of Control Science and Engineering, Dalian University of Technology, Dalian, 116024, China · Pika Labs · Department of Automation, Shanghai Jiao Tong University, Shanghai, 200240, China +1

Mar 2, 2026J/K move · Enter open · S save

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts

Xianqi Wang, Hao Yang, Hangtian Wang, Junda Cheng+3

Huazhong University of Science and Technology · Optics Valley Laboratory

Stereo Matching Visual Prompt Learning

Open paper AskPDF arXiv

Modern stereo matching methods have leveraged monocular depth foundation models to achieve superior zero-shot generalization performance. However, most existing methods primarily focus on extracting robust features for cost volume construction or disparity initialization. At the same time, the iterative refinement stage, which is also crucial for zero-shot generalization, remains underexplored. Some methods treat monocular depth priors as guidance for iteration, but conventional GRU-based architectures struggle to exploit them due to the limited representation capacity. In this paper, we propose Prompt Recurrent Unit (PRU), a novel iterative refinement module based on the decoder of monocular depth foundation models. By integrating monocular structure and stereo motion cues as prompts into the decoder, PRU enriches the latent representations of monocular depth foundation models with absolute stereo-scale information while preserving their inherent monocular depth priors. Experiments demonstrate that our PromptStereo achieves state-of-the-art zero-shot generalization performance across multiple datasets, while maintaining comparable or faster inference speed. Our findings highlight prompt-guided iterative refinement as a promising direction for zero-shot stereo matching.

Abstract

Stereo Matching

Explore similar work

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts

WAVE-Stereo: Warp-Aligned Volume Encoding for Stereo Matching

MatchAttention: Embedding Explicit Matching Constraints into Attention for Efficient Stereo Matching