arXiv subjects

Yiguang Liu

Publications and source records attributed to Yiguang Liu.

11 recordsLinked to original sources

arXiv2026

Rethinking Monocular Depth Embedding for Generalized Stereo Matching

Generally, monocular methods capture rich contextual priors but lack geometric precision, whereas stereo methods are geometrically accurate yet struggle in textureless and occluded regions. Several approaches attempt to combine their strengths to enhance the generalization of stereo matching (SM) by aligning monocular depth with stereo information. However, establishing a stable and generalizable alignment is challenging, and unreliable monocular cues can substantially degrade performance. This paper rethinks monocular depth embedding. First, to prevent shortcut learning, we reduce branch coupling instead of expanding network width. Second, we construct soft constraints instead of hard ones from monocular depth to improve tolerance to monocular depth errors. Based on the principles, we integrate monocular information into both feature extraction and GRU iterations. Specifically, the monocular depth map is fused with the RGB image to sharpen depth boundary perception and suppress matching ambiguities. The fused image is then used for feature extraction, allowing the contextual features to encode global geometric information. Furthermore, the monocular depth gradient feature is employed to guide disparity updates, helping to escape local oscillations. Finally, to address the boundary blurring of supervised disparity caused by data augmentation, we propose an edge confidence estimation method and an edge-aware loss function. Our method achieves state-of-the-art (SOTA) performance on multiple standard benchmarks, demonstrating excellent generalization while improving accuracy. The code is available at https://github.com/linliboabc-maker/stereo-matching-digital.

cs.CV↗

arXiv2025

Prototype-Based Pseudo-Label Denoising for Source-Free Domain Adaptation in Remote Sensing Semantic Segmentation

Source-Free Domain Adaptation (SFDA) enables domain adaptation for semantic segmentation of Remote Sensing Images (RSIs) using only a well-trained source model and unlabeled target domain data. However, the lack of ground-truth labels in the target domain often leads to the generation of noisy pseudo-labels. Such noise impedes the effective mitigation of domain shift (DS). To address this challenge, we propose ProSFDA, a prototype-guided SFDA framework. It employs prototype-weighted pseudo-labels to facilitate reliable self-training (ST) under pseudo-labels noise. We, in addition, introduce a prototype-contrast strategy that encourages the aggregation of features belonging to the same class, enabling the model to learn discriminative target domain representations without relying on ground-truth supervision. Extensive experiments show that our approach substantially outperforms existing methods.

cs.CV↗

arXiv2024

Low-light Stereo Image Enhancement and De-noising in the Low-frequency Information Enhanced Image Space

Unlike single image task, stereo image enhancement can use another view information, and its key stage is how to perform cross-view feature interaction to extract useful information from another view. However, complex noise in low-light image and its impact on subsequent feature encoding and interaction are ignored by the existing methods. In this paper, a method is proposed to perform enhancement and de-noising simultaneously. First, to reduce unwanted noise interference, a low-frequency information enhanced module (IEM) is proposed to suppress noise and produce a new image space. Additionally, a cross-channel and spatial context information mining module (CSM) is proposed to encode long-range spatial dependencies and to enhance inter-channel feature interaction. Relying on CSM, an encoder-decoder structure is constructed, incorporating cross-view and cross-scale feature interactions to perform enhancement in the new image space. Finally, the network is trained with the constraints of both spatial and frequency domain losses. Extensive experiments on both synthesized and real datasets show that our method obtains better detail recovery and noise removal compared with state-of-the-art methods. In addition, a real stereo image enhancement dataset is captured with stereo camera ZED2. The code and dataset are publicly available at: https://www.github.com/noportraits/LFENet.

cs.CV↗

arXiv2021

PHI-MVS: Plane Hypothesis Inference Multi-view Stereo for Large-Scale Scene Reconstruction

PatchMatch based Multi-view Stereo (MVS) algorithms have achieved great success in large-scale scene reconstruction tasks. However, reconstruction of texture-less planes often fails as similarity measurement methods may become ineffective on these regions. Thus, a new plane hypothesis inference strategy is proposed to handle the above issue. The procedure consists of two steps: First, multiple plane hypotheses are generated using filtered initial depth maps on regions that are not successfully recovered; Second, depth hypotheses are selected using Markov Random Field (MRF). The strategy can significantly improve the completeness of reconstruction results with only acceptable computing time increasing. Besides, a new acceleration scheme similar to dilated convolution can speed up the depth map estimating process with only a slight influence on the reconstruction. We integrated the above ideas into a new MVS pipeline, Plane Hypothesis Inference Multi-view Stereo (PHI-MVS). The result of PHI-MVS is validated on ETH3D public benchmarks, and it demonstrates competing performance against the state-of-the-art.

cs.CV↗

arXiv2021

An Elegant Inequality

A new inequality, $(x)^{p}+(1-x)^{\frac{1}{p}}\leq1$ for $p \geq 1$ and $\frac{1}{2} \geq x \geq 0$ is found and proved. The inequality looks elegant as it integrates two number pairs ($x$ and $1-x$, $p$ and $\frac{1}{p}$) whose summation and product are one. Its right hand side, $1$, is the strict upper bound of the left hand side. The equality cannot be categorized into any known type of inequalities such as Hölder, Minkowski etc. In proving it, transcendental equations have been met with, so some novel techniques have been built to get over the difficulty.

math.GM↗

arXiv2021

Learning Structral coherence Via Generative Adversarial Network for Single Image Super-Resolution

Among the major remaining challenges for single image super resolution (SISR) is the capacity to recover coherent images with global shapes and local details conforming to human vision system. Recent generative adversarial network (GAN) based SISR methods have yielded overall realistic SR images, however, there are always unpleasant textures accompanied with structural distortions in local regions. To target these issues, we introduce the gradient branch into the generator to preserve structural information by restoring high-resolution gradient maps in SR process. In addition, we utilize a U-net based discriminator to consider both the whole image and the detailed per-pixel authenticity, which could encourage the generator to maintain overall coherence of the reconstructed images. Moreover, we have studied objective functions and LPIPS perceptual loss is added to generate more realistic and natural details. Experimental results show that our proposed method outperforms state-of-the-art perceptual-driven SR methods in perception index (PI), and obtains more geometrically consistent and visually pleasing textures in natural image restoration.

eess.IV↗

arXiv2020

Disentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation

Recent works in domain adaptation always learn domain invariant features to mitigate the gap between the source and target domains by adversarial methods. The category information are not sufficiently used which causes the learned domain invariant features are not enough discriminative. We propose a new domain adaptation method based on prototype construction which likes capturing data cluster centers. Specifically, it consists of two parts: disentanglement and reconstruction. First, the domain specific features and domain invariant features are disentangled from the original features. At the same time, the domain prototypes and class prototypes of both domains are estimated. Then, a reconstructor is trained by reconstructing the original features from the disentangled domain invariant features and domain specific features. By this reconstructor, we can construct prototypes for the original features using class prototypes and domain prototypes correspondingly. In the end, the feature extraction network is forced to extract features close to these prototypes. Our contribution lies in the technical use of the reconstructor to obtain the original feature prototypes which helps to learn compact and discriminant features. As far as we know, this idea is proposed for the first time. Experiment results on several public datasets confirm the state-of-the-art performance of our method.

cs.CV↗

arXiv2020

Complex-order Derivative and Integral Filters and its Applications

In this paper, complex-order derivative and integral filters are proposed, which are consistent with the filters with fractional derivative and integral orders. Compared with the filters designed only with real orders, complex order filters can reveal more details of input signals, and this can benefit a large number of tasks. The tremendous effect of the proposed complex-order filters, has been verified by several image processing examples. Especially, for the challenging problem indicating the diseased regions in prostate TRUS images, the proposed complex order filters look very promising. It is very astonishing that, indicating the diseased regions is fulfilled by complex-order integral, not by derivative. This is completely against the traditional views that using derivative operators to achieve the goal.

eess.SP↗

arXiv2018

A Unifying Decomposition and Reconstruction Model for Discrete Signals

Decomposing discrete signals such as images into components is vital in many applications, and this paper propose a framework to produce filtering banks to accomplish this task. The framework is an equation set which is ill-posed, and thus have many solutions. Each solution can form a filtering bank consisting of two decomposition filters, and two reconstruction filters. Especially, many existing discrete wavelet filtering banks are special cases of the framework, and thus the framework actually makes the different wavelet filtering banks unifiedly presented. Moreover, additional constraints can impose on the framework to make it well-posed, meaning that decomposition and reconstruction (D&R) can consider the practical requirements, not like existing discrete wavelet filtering banks whose coefficients are fixed. All the filtering banks produced by the framework can behave excellently, have many decomposition effect and precise reconstruction accuracy, and this has been theoretically proved and been confirmed by a large number experimental results.

eess.IV↗

arXiv2015

Study on Sparse Representation based Classification for Biometric Verification

In this paper, we propose a multimodal verification system integrating face and ear based on sparse representation based classification (SRC). The face and ear query samples are first encoded separately to derive sparsity-based match scores, and which are then combined with sum-rule fusion for verification. Apart from validating the encouraging performance of SRC-based multimodal verification, this paper also dedicates to provide a clear understanding about the characteristics of SRC-based biometric verification. To this end, two sparsity-based metrics, i.e. spare coding error (SCE) and sparse contribution rate (SCR), are involved, together with face and ear unimodal SRC-based verification. As for the issue that SRC-based biometric verification may suffer from heavy computational burden and verification accuracy degradation with increase of enrolled subjects, we argue that it could be properly resolved by exploiting small random dictionary for sparsity-based score computation, which consists of training samples from a limited number of randomly selected subjects. Experimental results demonstrate the superiority of SRC-based multimodal verification compared to the state-of-the-art multimodal methods like likelihood ratio (LLR), support vector machine (SVM), and the sum-rule fusion methods using cosine similarity, meanwhile the idea of using small random dictionary is feasible in both effectiveness and efficiency.

cs.CV↗

arXiv2014

A random algorithm for low-rank decomposition of large-scale matrices with missing entries

A Random SubMatrix method (RSM) is proposed to calculate the low-rank decomposition of large-scale matrices with known entry percentage ρ. RSM is very fast as the floating-point operations (flops) required are compared favorably with the state-of-the-art algorithms. Meanwhile RSM is very memory-saving. With known entries homogeneously distributed in the given matrix, sub-matrices formed by known entries are randomly selected. According to the just proved theorem that subspace related to smaller singular values is less perturbed by noise, the null vectors or the right singular vectors associated with the minor singular values are calculated for each submatrix. The vectors are the null vectors of the corresponding submatrix in the ground truth of the given large-scale matrix. If enough sub-matrices are randomly chosen, the low-rank decomposition is estimated. The experimental results on random synthetical matrices with sizes such as 131072X1024 and on real data sets indicate that RSM is much faster and memory-saving, and, meanwhile, has considerable high precision achieving or approximating to the best.

math.NA↗