DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch

Duggal, Shivam; Wang, Shenlong; Ma, Wei-Chiu; Hu, Rui; Urtasun, Raquel

doi:10.1109/iccv.2019.00448

Cited by 257 publications

(202 citation statements)

References 36 publications

Supporting

Mentioning

175

Contrasting

Order By: Relevance

“…Then we apply another 1000 epochs to fine-tune our model on separate KITTI 2012/2015 datasets, with initial learning rate of 3 × 10 −5 and same schedule as before. Method GCNet [5] PSMNet [6] GANet [14] DeepPruner [18] DispNetC [7] StereoNet [19] AANet [9]…”

Section: Resultsmentioning

confidence: 99%

Hierarchical Context Guided Aggregation Network for Stereo Matching

Peng

Xie

Huang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Nowadays, CNN-based stereo matching methods achieved remarkable performance, and how to efficiently exploit contextual information in cost aggregation stage is the key to improve performance. In this paper, we propose a simple yet efficient network named Hierarchical Context Guided Aggregation Network (HCGANet). Specifically, a novel cost aggregation module is developed to replace widely used 3D convolutions. Firstly, we construct pyramid cost volumes which carry multi-level distinctive and discriminative representation. Additionally, an intra-level aggregation module is presented for single-level regularization and contextual information learning. Moreover, we develop an inter-level aggregation module to hierarchically regularize cost volumes via the guidance from coarser scales. The proposed aggregation module is lightweight and complementary, further improving the robustness and performance of disparity estimation. Extensive experiments demonstrate that the proposed method achieves superior results for both efficiency and accuracy on Scene-Flow and KITTI benchmarks.

show abstract

Section: Resultsmentioning

confidence: 99%

Hierarchical Context Guided Aggregation Network for Stereo Matching

Peng

Xie

Huang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Our work is related to measuring uncertainty for 3D reconstruction. [5], [22] proposed to learn uncertainty from groundtruth for stereo. [21], [25] learned confidences based on deviation from median disparity.…”

Section: Related Workmentioning

confidence: 99%

An Adaptive Framework for Learning Unsupervised Depth Completion

Wong

Fei

Hong

et al. 2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

We present a method to infer a dense depth map from a color image and associated sparse depth measurements. Our main contribution lies in the design of an annealing process for determining co-visibility (occlusions, disocclusions) and the degree of regularization to impose on the model. We show that regularization and co-visibility are related via the fitness (residual) of model to data and both can be unified into a single framework to improve the learning process. Our method is an adaptive weighting scheme that guides optimization by measuring the residual at each pixel location over each training step for (i) estimating a soft visibility mask and (ii) determining the amount of regularization. We demonstrate the effectiveness our method by applying it to several recent unsupervised depth completion methods and improving their performance on public benchmark datasets, without incurring additional trainable parameters or increase in inference time.

show abstract

“…For performance evaluations, we compare the proposed method to other stereo matching algorithms. The compared methods include adaptive support weight (ASW) [21], segmentation-based adaptive support weight (S-ASW) [23], plant leaf stereo matching (LP-SM) [36], edge-based stereo matching method (E-SM) [37], stereo matching implemented on GPU platform [31], AdaStereo [38], comparative evaluation of SGM variants for dense stereo matching (tMGM) [39], learning-based disparity estimation (iResNet) [40], and DeepPruner [41] methods. Tables 3 and 4 show that the performance of the proposed multi-scale ASW is superior to traditional ASW and other methods.…”

Section: Comparisons With Other Approachesmentioning

confidence: 99%

Shape-reserved stereo matching with segment-based cost aggregation and dual-path refinement

Huang

Chan

et al. 2020

J Image Video Proc.

View full text Add to dashboard Cite

Stereo matching is one of the most important topics in computer vision and aims at generating precise depth maps for various applications. The major challenge of stereo matching is to suppress inevitable errors occurring in smooth, occluded, and discontinuous regions. In this paper, the proposed stereo matching system uses segment-based superpixels and matching cost. After determination of edge and smooth regions and selection of matching cost, we suggest the segment-based adaptive support weights in cost aggregation instead of color similarity and spatial proximity only. The proposed dual-path depth refinements use the cross-based support region by referring texture features to correct the inaccurate disparities with iterative procedures to improve the depth maps for shape reserving. Specially for leftmost and rightmost regions, the segment-based refinement can greatly improve the mismatched disparity holes. The experimental results show that the proposed system can achieve higher accurate depth maps than the conventional methods.

show abstract

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch

Cited by 257 publications

References 36 publications

Hierarchical Context Guided Aggregation Network for Stereo Matching

Hierarchical Context Guided Aggregation Network for Stereo Matching

An Adaptive Framework for Learning Unsupervised Depth Completion

Shape-reserved stereo matching with segment-based cost aggregation and dual-path refinement

Contact Info

Product

Resources

About