Diffusion models have become a rising star in image super-resolution (SR) tasks. However, it is not trivial to apply diffusion models for light field (LF) image SR, which requires maintaining the high-quality visual appearance of each sub-aperture image (SAI) and the angular consistency between the different SAIs. This paper proposes the first diffusion-based LF image SR model, namely LFSRDiff, by incorporating the LF disentanglement mechanism and residual modeling. Specifically, we introduce a disentangled U-Net (Distg U-Net) for diffusion models, enabling improved extraction and fusion of the spatial and angular information in LF images. Furthermore, we leverage residual modeling in diffusion to learn the residual between the upsampled low-resolution and the ground truth high-resolution, which significantly accelerates model training and yields superior results compared to direct learning. Extensive experiments conducted on the five datasets demonstrate the effectiveness of our approach, which can produce realistic SR results and achieve the highest perceptual metric in terms of LPIPS. Code is publicly available at https://github.com/chaowentao/LFSRDiff.

Craniofacial superimposition is a crucial forensic science technique to identify human remains by matching skulls to facial images. However, this task is challenging due to significant morphological differences between skulls and faces, limited paired samples, and high data dimensionality. We proposed a geometric feature-driven metric learning method for craniofacial superimposition to address these issues. Firstly, we extracted geometric features, including depth, curvature, and elevation of 3D craniofacial data, to generate 2D maps of structured representations enriched with geometric details. Next, we novelly designed a Triplet Network for geometric feature-driven metric learning, which leverages triplet loss to learn discriminative embeddings and effectively handle the limited paired data problem. By incorporating the Sinkhorn Distance as an additional constraint, we aligned the skull and face data distributions, enhancing the matching precision. We conducted extensive experiments on a 3D craniofacial dataset, achieving a maximum accuracy of 99.45% on curvature maps, surpassing state-of-the-art methods. Our code will be available after publication at https://github.com/Lqd-js/cranial-superimposition.

Inverse rendering has been extensively explored with the advent of neural implicit fields. However, existing methods struggle to model global illumination and to fully integrate volume rendering with physically based rendering in a single stage. To address this issue, we propose TIRPL, a tailored-made inverse rendering method for point-light scenes. Our method efficiently combines volume rendering and physically based rendering to jointly optimize scene geometry, materials, and global illumination from multi-view images in a single stage. We design an indirect color network and allow the light intensity to be learnable to estimate global illumination. Additionally, a feature vector and a tailored-made light intensity decay rate are devised to combine volume rendering and physically based rendering in a single stage. Extensive experiments are conducted in both real and synthetic datasets, showing the effectiveness of our method.

3D facial reconstruction plays a crucial role in virtual reality and entertainment. Impressive rendering and animation effects have been achieved through recent advances. Existing Gaussian avatar models generate diverse expressions, but the corresponding texture changes are not so satisfactory, and their geometric structure often falls short. In response to these challenges, we propose a 3D head avatar with remarkable geometry, which can control expression variations and enable facial texture information to change along with expressions. To achieve this effect, we combine the 2D Gaussian field with the facial parametric model, use the mesh to drive Gaussian field, design a fine-tuning field for the mouth area to fit distorted expressions, and simultaneously design a color variation module to simulate changes in facial wrinkles and skin. Experiments demonstrate that our avatar model exhibits excellent performance in both appearance details and geometric shapes.

Data augmentation (DA) is an effective approach for enhancing model performance with limited data, such as light field (LF) image super-resolution (SR). LF images inherently possess rich spatial and angular information. Nonetheless, there is a scarcity of DA methodologies explicitly tailored for LF images, and existing works tend to concentrate solely on either the spatial or angular domain. This paper proposes a novel spatial and angular DA strategy named MaskBlur for LF image SR by concurrently addressing spatial and angular aspects. MaskBlur consists of spatial blur and angular dropout two components. Spatial blur is governed by a spatial mask, which controls where pixels are blurred, i.e., pasting pixels between the low-resolution and high-resolution domains. The angular mask is responsible for angular dropout, i.e., selecting which views to perform the spatial blur operation. By doing so, MaskBlur enables the model to treat pixels differently in the spatial and angular domains when super-resolving LF images rather than blindly treating all pixels equally. Extensive experiments demonstrate the efficacy of MaskBlur in significantly enhancing the performance of existing SR methods. We further extend MaskBlur to other LF image tasks such as denoising, deblurring, low-light enhancement, and real-world SR.

3D face shape completion is a necessary pre-process for various facial applications as they are often mutilated due to the acquiring environment or occlusion. However, it is challenging to ensure identity consistency when completing faces with large missing regions. Therefore, we introduce craniofacial information to supervise the completion of face shapes. Firstly, a novel dual encoder-decoder structure for face depth image inpainting is constructed by combining dilated convolution and the coherent semantic attention mechanism, guaranteed to generate smooth results with complete semantic information even in the presence of large missing regions in the face model. Then, we innovatively design a craniofacial superimposition module to determine the probability that the inpainted face and corresponding skull come from the same person, constraining the inpainting network to learn identity consistency information. Finally, extensive experimental results show that our method can effectively complete 3D face shapes containing large arbitrary missing regions while guaranteeing identity consistency.

A single light field image, containing multiple views, can be utilized in conjunction with estimated depth map to generate three-dimensional (3D) point cloud. It is noteworthy that many depth estimation algorithms frequently produce depth maps plagued by issues such as holes and blurred edges. Many algorithms use global optimization directly to optimize depth maps without considering the effects of holes and blurred edges, resulting in the loss of the sharp features of the point cloud. Different from their methods, we consider both holes and blurry edges as outlier points. Then, we classify angular sampling images based on color consistency differences and employ interclass distances to detect outlier points. With the help of the outlier mask, we can obtain the depth confidence for each point. Combining with the depth confidence, we define a weighting coefficient to determine the optimization neighborhood of the outlier point. Finally, the point cloud generated by the depth map can be further optimized based on the outlier mask. Experimental results on synthetic and real datasets demonstrate the effectiveness of the proposed algorithm.

Point cloud completion aims at recovering the complete point cloud from an incomplete input. A general scheme is to generate a group of coarse points first that generalize the global shape, and then reconstruct dense point cloud by upsampling operation. In this paper, we propose a novel point cloud completion network, SkeletonFormer, to tackle two critical challenges: fully utilizing the information from the point cloud with various incompleteness degree and recovering high-quality geometric structures. To increase the universality of our model to diverse input, we propose a score mechanism to dynamically select proper skeleton points that can adapt to various degree of deficiency. To improve the perception of the target object, we use self-projected depth images as an augmented modality representation to observe the input. A modality unification module is designed to fuse the depth image feature and the point cloud feature, and it can alleviate the intrinsic differences among multi-modal information. The fused feature is used to assist the prediction of the skeleton points that represent the holistic complete object. Furthermore, by fully leveraging local geometric information, we design a novel and effective DeconvNet to reconstruct fine-grained patterns around the skeleton points. Extensive experiments demonstrate that our SkeletonFormer surpasses existing works by a large margin and achieves state-of-the-art performance on various benchmarks.

Facial expressions are an essential part of human emotional communication, and micro-expressions (MEs), as transient and imperceptible non-verbal signals, can potentially reveal real human emotions. However, subtle motion variations, limited and unbalanced samples make micro-expression recognition (MER) challenging. In this paper, we design a novel dual-branch learning framework of multi-level flow-driven attention for micro-expression recognition (MFDAN), which innovatively integrates optical flow prior to guide the attention learning in the image encoding branch, enabling the model to focus on the most discriminative facial regions for subtle motion patterns. Firstly, we extract optical flow information by an optical flow encoding module. Then, in the image coding module, we construct a Transformer structure containing an optical flow-driven attention mechanism, which can effectively locate the interest region of micro-expressions in the image according to the position information of optical flow to capture more sensitive and fine-grained micro-expressions. By interoperating prior knowledge with data learning, and introducing the Dropkey operation and Focal Loss, our method can handle subtle micro-expression features on small imbalanced datasets. Through extensive experiments on three independent datasets and a composite database, including SMIC-HS, SAMM, and CASME II, robust leave-one-subject-out (LOSO) evaluation results show that our method outperforms state-of-the-art methods especially on the composite database.

Depth maps suffer from multiple kinds of degradation such as noise and low resolution, due to the limitations of sensors. To improve the spatial resolution and quality of depth maps, RGB-D-based depth super-resolution (SR) methods utilize the corresponding color image to provide extra structure information. However, the inconsistency between the color texture and depth structure can lead to texture-copying artifacts if the two kinds of features are fused without selection. In this article, we propose a novel coarse-to-fine framework for RGB-D-based depth SR, which consists of two sub-networks, i.e., CONet for coarse SR and RFNet for refinement. Through the proposed coarse supervision strategy, CONet can alleviate multiple degradations in depth maps and assist with further SR in the refinement stage. Moreover, the branch attention module (BAM) is incorporated in the RFNet to adaptively select important information from RGB-D features and suppress the texture-copying artifact. Additionally, we propose an edge-aware spatial attention module (ESAM) to further locate and restore the depth discontinuity in the fused RGB-D features. Extensive experiments on multiple benchmarks demonstrate that compared to the state-of-the-art methods, the proposed method achieves improved results both quantitatively and qualitatively.

Light field can be decoded into multiple representations and provides valuable focus and depth information. This breakthrough overcomes the limitations of traditional 2D and 3D saliency detection methods, opening up new possibilities for more accurate and comprehensive analysis of visual scenes. To tackle the challenges of inaccurate edge prediction and effectively leverage the rich multi-modal light field information, we propose a gated multi-modal edge refinement network (GMERNet). It first obtains the preliminary position and structure information of the salient object and then gradually refines the object edge. This involves two modules: gated multi-modal feature complement (GMFC) module and progressive edge refinement (PER) module. The GMFC module captures dependencies across the all-in-focus image and its corresponding focal stack and depth map, effectively aggregating multiple features through gate mechanisms. The PER module progressively refines edges by combining salient object features with edge features through a cascaded structure. Experimental results demonstrate that GMERNet achieves state-of-the-art performance on five benchmark datasets and shows significant advantages in extracting salient objects with complex edges.

Landmark localization plays a significant role in craniofacial registration, reconstruction, and authentication. The key challenges for localizing landmarks on point cloud craniofacial models include irregular structures, non-uniform densities, and uncertain local regions. In this paper, we propose an end-to-end regression network that can directly estimate craniofacial landmarks on point cloud models. The proposed network utilizes edge convolution to extract local features and pooling layers to aggregate global features. It realizes the end-to-end regression for landmark localization. Experimental results demonstrate that our method is robust on point clouds with sparse and unevenly distributed sampling. It can produce accurate, controllable, and efficient 3D landmarks.

Abstract Face attribute classification (FAC) has received considerable attention due to its excellent application value in bio‐metric verification and face retrieval. Current FAC methods suffer two typical challenges: complex inter‐attribute correlations and imbalanced learning. Aims at the challenges, presents an end‐to‐end FAC framework with integrated use of multiple strategies, which consists of a convolutional neural network (CNN) and a graph convolutional network (GCN). The GCN is used to model the semantic correlations among attributes and capture inter‐dependency among them. The correlation information learnt via the GCN is used to guide the learning of the inter‐dependent classification features of the FAC network. An adaptive thresholding strategy and a boosting scheme are adopted to alleviate the effect of the class‐imbalance. To deal with the task imbalance problem, a new dynamic weighting scheme is proposed to update the weight of each attribute classification task in the training process. We apply four evaluation metrics to evaluate the proposed method. Experimental results show all the proposed strategies are effective, and our approach outperforms state‐of‐the‐art FAC methods on two challenging datasets CelebA and LFWA.

Bottom-up human pose estimation has raised more investigation in recent years, especially 2D keypoints regression. However, the state-of-art DEKR [1] still has some aspects (e.g., speed and accuracy) to be improved. In this paper, we propose a new framework named DEKRv2, which has been enhanced compared to DEKR. When DEKR calculates the offset of each keypoint, it only considers the features of the current keypoint and neglects the constraints between the adjacent keypoints. We adopt a coarse-to-fine feature extraction method to obtain a more accurate feature location of keypoints for this problem. We also find that the multibranch network in DEKR is very time-consuming because it is serial. We designed a more effective module based on Group Convolution to replace the multi-branches network in DEKR, and it can reduce reasoning time. Experiments on the CrowdPose dataset show that our method achieves superior compared with DEKR in speed or accuracy, respectively. In the single-scale test, our method obtains 66.6 mAP, 0.6 higher than DEKR. The codes and models are available at https://github.com/chaowentao/DEKRv2.

The application of face depth maps is promising but limited due to the multiple degradations introduced by depth sensors, such as low spatial resolution, noise and blurry edges. In this paper, we propose a novel coarse-to-fine framework that progressively denoises and super-resolves face depth maps with two stages. The coarse stage consists of a denoising sub-network and an edge inference sub-network, and it recovers a denoised coarse depth map and an edge prior to assist the following depth refinement. The refinement stage consists of multiple attentive feature selection and fusion (AFSF) blocks that can enrich the feature diversity and aggregate important features selectively. Moreover, a residual learning scheme is used in the refinement stage to enhance the details. Extensive experiments on both synthetic and real-world face depth datasets demonstrated the superiority of our method over several state-of-the-art methods.

Craniofacial reconstruction is fundamental in resolving forensic cases. It is rather challenging due to the complex topology of the craniofacial model and the ambiguous relationship between a skull and the corresponding face. In this paper, we propose a novel approach for 3D craniofacial reconstruction by utilizing Conditional Generative Adversarial Networks (CGAN) based on craniofacial depth map. More specifically, we treat craniofacial reconstruction as a mapping problem from skull to face. We represent 3D cran- iofacial shapes with depth maps, which include most craniofacial features for identification purposes and are easy to generate and apply to neural networks. We designed an end-to-end neural networks model based on CGAN then trained the model with paired craniofacial data to automatically learn the complex nonlinear relationship between skull and face. By introducing body mass index classes(BMIC) into CGAN, we can realize objective reconstruction of 3D facial geometry according to its skull, which is a complicated 3D shape generation task with different topologies. Through comparative experiments, our method shows accuracy and verisimilitude in craniofacial reconstruction results.

Recently, Graph Convolution Network (GCN) and Temporal Convolution Network (TCN) are introduced into traffic prediction and achieve state-of-the-art performance due to their good ability for modeling the spatial and temporal property of traffic data. In spite of having good performance, the current methods generally focus on the traffic measurement of road segments, i.e. the nodes of traffic flow graph, while the edges of the graph, which represent the correlation of traffic data of different road segments and form the affinity matrix for GCN, are usually constructed according to the structure of road network, but the spatial and temporal properties are not well exploited in their theories. In this paper, we propose a Dual Dynamic Spatial-Temporal Graph Convolution Network (DDSTGCN), which not only models the dynamic property of the nodes of the traffic flow graph but also captures the dynamic spatial-temporal feature of the edges by transforming the traffic flow graph into its dual hypergraph. The traffic prediction is enhanced by the collaborative convolutions on the traffic flow graph and its dual hypergraph. The proposed method is evaluated by extensive traffic prediction experiments on six real road datasets and the results show that it outperforms state-of-the-art related methods. Source codes are available athttps://github.com/j1o2h3n/DDSTGCN.

Geometric primitives contained in three‐dimensional (3D) point clouds can provide the meaningful and concise abstraction of 3D data, which plays a vital role in improving 3D vision‐based intelligent applications. However, how to efficiently and robustly extract multiple geometric primitives from point clouds is still a challenge, especially when multiple instances of multiple classes of geometric primitives are present. In this study, a novel energy minimisation‐based algorithm for multi‐class multi‐instance geometric primitives extraction from the 3D point cloud is proposed. First, an improved sampling strategy is proposed to generate model hypotheses. Then, an improved strategy to establish the neighbourhood is proposed to help construct and optimise an energy function for points labelling. After that, hypotheses and parameters of models are refined. Iterate this process until the energy does not decrease. Finally, models of multi‐class multi‐instance geometric primitives are simultaneously and robustly extracted from the 3D point cloud. In comparison with the state‐of‐the‐art methods, it can automatically determine the classes and numbers of geometric primitives in the 3D point cloud. Experimental results with synthetic and real data validate the proposed algorithm.

In recent years, consumer depth cameras have been widely used in digital entertainment and human‐machine interaction due to the advantages of real‐time performance and low cost. Facial depth maps have shown great potential in 3D‐face‐related studies. However, disadvantages of low resolution and precision limit its further applications. In this work, the authors propose an edge‐guided convolutional neural network for single facial depth map super‐resolution. It consists of two parts: an edge prediction sub‐network and a depth reconstruction sub‐network. The edge prediction sub‐network generates an edge guidance map to guide the depth reconstruction sub‐network to recover sharp edges and fine structures. Effective data augmentation methods are proposed as well. The network is patch‐based and able to cope with any size of the input depth maps. In addition, it is insensitive to the face pose since the synthetic training dataset they generated covers a wide range of face poses. The proposed method is validated with three datasets including a synthetic facial depth data set, a real Kinect V2 facial depth data set and Middlebury Stereo Data set. Experimental results show that it outperforms the state‐of‐the‐art methods on all the three data sets.

Age is an important biometric feature of human face. Estimating the specific age of facial images is challenging, because of face aging's highly nonlinearity and randomness. Commonly age predictors are based on classification or regression method, which may be affected greatly by the category number or data distribution of the labelled samples. In this paper, we design a parallel deep neural network, called PGR-Net. It is a unified learning model which combines the merits of traditional classification methods and regression methods. The model consists of a classification network and several age regressors. The classification network is designed to divide facial images into several age groups, and a regressor is trained for each group separately. We train the classification network and the re-gressors in parallel, and perform age estimation with the regressor of the group predicted by the classification network. Experiments show that the proposed approach is fairly competitive compared with the state-of-the-art methods on two public datasets.

How to estimate accurately the homography is always a challenging problem in computer vision. In the reported literature, the measurement error of the image points is usually assumed to obey isotropic Gaussian distribution. However, real data very seldom follows this assumption. This paper proposes an estimation of homography under the assumption of image point errors following elliptical distribution, which is more coincident with real data. In the proposed method, the adaptive-scale elliptical residual kernel consensus (ASERKC) robust estimator is used to filter out inliers which are utilized to compute homography. Then, the elliptical weighted L-M (EW L-M) algorithm is optimized the homography. The experimental results show that the proposed method may present a more accurate homography. Especially when we applied it to incremental structure-from-motion (SFM), we find that the exact homography matrix is useful to select a better initial image pairs which can help obtain a more complete 3D points cloud.

Face sketch-photo synthesis has important usage in law enforcement and human authentication. Due to the sparse information (no color or texture), the abstraction level, the diversity of sketches, and the domain gap between sketch and photo, it is challenging to synthesize a photo-realistic photo from an input sketch. Moreover, the deficiency of data also restricts the synthesis performance. In this paper, we present a high-fidelity face sketch-photo synthesis method using Generation Adversarial Network (GAN). Our network adopts a deep residual U-Net as generator and a Patch-GAN with residual blocks as discriminator. We design effective loss functions by enforcing pixels, edges and high-level features of the produced face photos. Moreover, we augment the CUHK sketch dataset using an effective sampling method. With the improved GAN and augmented dataset, we achieve high-fidelity face photos. Qualitative and quantitative experiments demonstrate the approach outperforms other method. Further experiments with a sketch-based photo editing application also validate the performance of our method.

Face sketch is the main approach to find suspect in law enforcement, especially in many cases when facial attribute descriptions of suspects by witnesses are available. Face sketch synthesized from facial attribute text can also be used in sketch based face recognition. While most previous work focus on face photo to sketch synthesis, the problem of sketch synthesis with facial attribute text has not been explored yet. The problem is challenging due to two facts: firstly, no database of face attribute text to sketch is available; secondly, it is hard to synthesize high-quality face sketches due to the ambiguity and complexity of text description. In this paper, we propose a face sketch synthesis approach with text using Stagewise-GAN. Our contributions lie in two aspects: 1) we construct the first text to face sketch database. The database, namely Text2Sketch dataset, is annotated with CUFSF dataset of 1194 sketches. For each sketch, an attribute description is labelled; 2) we synthesize vivid face sketches using Stagewise-GAN. We use user study, face retrieval performance with synthesized sketch, and quantitative results for evaluation. Experimental results show the effectiveness of our approach.

In this paper, we present a novel method on image calibration, utilizing Total Least Square (TLS) method and Feedforward Neural Network, to solve the aberration problem of LAMOST two-dimensional astronomical spectral images. In our method, training sample set is generated with domain knowledge, from which a number of discrete points are are extracted from spectral images with fiber tracing method, and output vectors are formed by the corresponding calibrated points, obtained by utilizing the TLS method. The Feed-forward Neural Network is trained to obtain the transformation matrix, casting about for the matching relationship between the input and output sets. We also perform comparative experiments on fiber tracing and spectrum extraction results between calibrated spectral images and uncalibrated spectral images, the results show an advantage of higher accuracy and precision by our proposed method.

Face reconstruction from skull, called as Craniofacial Reconstruction (CFR), is a useful technique to identify an unknown decomposed corpse if no other evidence is available. Traditional manual methods greatly depend on the experience of sculptors, so that the results are highly subjective, and the whole process is time consuming. Recent years, 3D data acquiring technology becomes consummate, and machine learning techniques raise a tidal wave in academia and industry. Researchers turn to finding computer aided solutions, especially the supervised machine learning technique, for craniofacial reconstruction. Least Squares Canonical Dependency Analysis (LSCDA) is a dimension reduction method, which aims at finding subspaces where the dependency measured by Least Squares Mutual Information (LSMI) of two variables reaches maximum. This paper proposes a new method for craniofacial reconstruction based on LSCDA. First, two statistical shape models for skull and skin are constructed respectively by Principle Component Analysis (PCA). Then the subspaces of maximum dependency of face and skull are extracted in the shape parameter spaces via LSCDA. Finally, according to such dependency, the relationship model between skulls and skins is established by Least Squares Support Vector Regression (LSSVR), which is used to reconstruct the facial appearances for an unknown skull. Experiment results show that the proposed method is effective.

The success of deep learning proves that deep models are able to achieve much better performance than shallow models in representation learning. However, deep neural networks with auto-encoder stacked structure suffer from low learning efficiency since common used training algorithms are variations of iterative algorithms based on the time-consuming gradient descent, especially when the network structure is complicated. To deal with this complicated network structure problem, we employ a “divide and conquer” strategy to design a locally connected network structure to decrease the network complexity. The basic idea of our approach is to force the basic units of the deep architecture, e.g., auto-encoders, to extract local features in an analytical way without iterative optimization and assemble these local features into a unified feature. We apply this method to process astronomical spectral data to illustrate the superiority of our approach over other baseline algorithms. Furthermore, we investigate visual interpretations of high level features and the model to demonstrate what exactly the model learn from the data.

This paper proposed a face sketch synthesis method by using non-local means (NL-Means), which takes the advantage of the non-local self-similarity of face photo and sketch patches. With a learning database of individuals described by one face photo and one face sketch, we assume that, for a given individual, the NL-Means coefficient of a given face photo patch is the same as its corresponding sketch patch. In order to handle the visible seam due to intensity difference of neighbor overlapping patches, we use patch based optimal seam to enforce the consistency of synthesized overlapping sketch patches. Experimental results on CUHK Face Sketch Database illustrate that our method has the advantage of easy implementation and much less required training samples, meanwhile our method can achieve fairly competitive synthesis results.

Craniofacial reconstruction is to get a visual outlook of an individual from its skull. It is an important technology in both forensic medicine and archeology. This paper proposes a novel craniofacial reconstruction method based on least square support vector regression (LSSVR), which has the flexibility for uncovering nonlinear relationships between variables and is easy to solve. We firstly build statistical shape models for skulls and face skins respectively, and then train the LSSVR model in the shape parameter spaces. Given an unknown skull, we project it to the skull shape parameter space, and use the LSSVR model to reconstruct the corresponding face skin. Cross validation is used for parameter selection in LSSVR. Experiments are given on a data set including 150 training pairs of skull and skin samples and 58 testing ones. Comparisons with ridge regression and partial least square regression show that our method can reconstruct the craniofacial effectively and accurately.

Skull identification is an important subject for research in forensic medicine. Current research can be divided into two categories: 1) craniofacial superimposition and 2) craniofacial reconstruction. Both categories rely essentially on the accurate extraction and representation of the intrinsic relationship between the skull and face in terms of the morphology, which still remain unsolved. They have high uncertainty and a low identification capability. This paper proposes a novel skull identification method that matches an unknown skull with enrolled 3D faces, in which the mapping between the skull and face is obtained using canonical correlation analysis. Unlike existing techniques, this method needs no accurate relationship between the skull and face, and measures only the correlation between them. In order to measure the correlation more reliably and improve the identification capability of the correlation analysis model, a region fusion strategy is adopted. Experimental results validate the proposed method, and show that the region-based method can significantly boost the matching accuracy. The correct identification rate reaches 94% when using a CT data set. This paper can provide a theory support for research on craniofacial superimposition and craniofacial reconstruction.

Camera calibration is a necessary step to extract 3D information from 2D images. Since the ID object is easy to construct and without self-occlusion, the ID calibration proposed by Zhang has received many attentions. However, the progress in ID calibration mainly focuses on reducing restrictions on the ID object's movements. The calibration accuracy still demands improvements. In this paper, the computational model of ID calibration is reformulated, noises in ID calibration are analyzed with this model, and an heteroscedastic error-in- variables model-based ID calibration algorithm is proposed. In comparison with exiting algorithms, the proposed algorithm has advantages of high accuracy with a small number of measurements, rapid convergence and weak insensitivity to initial conditions. Experiments with both synthetic and real image data validate the proposed algorithm.

Catadioptric imaging systems are widely used in many applications such as robot navigation, surveillance or 3D reconstruction due to their large field of view. However, the catadioptric image has a larger deformation than the perspective image, which makes catadioptric camera calibration more difficult. Previous approaches using lines need conic fitting, which is a hard work for catadioptric images. This paper proposes a nonlinear method based on the constraint from the projection of a space line. A simple and intuitive estimate of the initial camera parameters is also presented, which can be used in some applications without requirement for high accuracy. The proposed method needs no conic fitting that highly affects the calibration accuracy. The validity of the proposed approach is shown by experiments.

Visual metrology methods with radial distorted images usually require a radial distortion model and a pre-calibration. In this paper, we propose a novel 3D metrology algorithm with at least three uncalibrated radial distorted images, and also derive a 2D metrology algorithm with at least two uncalibrated radial distorted images. The algorithm does not require a radial distortion model or calibrating camera intrinsic parameters except for radial distortion center, which can be usually known as a prior or computed easily, and correspondences of control points with known coordinates. The algorithm is of high accuracy, and robust to noise due to no requirement for specific radial distortion models. Experimental results show the feasibility and accuracy of the algorithm.

In this paper, a novel algorithm for the fundamental matrix estimation, called factorized 8-point algorithm, is presented. The factorized 8-point algorithm is composed of three steps: (1) The measurement matrix in the traditional 8-point algorithm is decomposed into two factor matrices; (2) By introducing some auxiliary variables, a new linear minimization problem is formed, where every element of its associated measurement matrix is simply either a measurement datum or a constant; (3) The fundamental matrix is determined by solving this minimization problem by a least squares method. Like the traditional 8-point algorithm and Hartley's normalized 8-point algorithm, the factorized 8-point algorithm is also completely linear. But unlike the normalized 8-point algorithm, the factorized 8-point algorithm does not need any pre-normalization step. Since every element of the measurement matrix in the factorized 8-point algorithm is a measurement datum or a constant, no amplification of measurement error is involved; the factorized 8-point algorithm can boost effectively the robustness of the estimation. Large numbers of experiments show that the factorized 8-point algorithm consistently outperforms the traditional 8-point algorithm. In addition, although the factorized 8-point algorithm is specially designed for fundamental matrix estimation, its basic principle can be generalized to other estimation problems in computer vision, such as camera projection matrix estimation, homography estimation, focus of expansion estimation, and trifocal tensor estimation.