Chamfer Distance Research Articles

Severity Stratification of Coronary Artery Disease Using Novel Inner Ellipse-Based Foveal Avascular Zone Biomarkers.

Given the similarities between the retinal and coronary microvasculature, the retina holds promising potential to serve as a non-invasive screening tool for coronary artery disease (CAD). We aimed to develop novel inner ellipse-based metrics and discern whether foveal avascular zone (FAZ) alterations can serve as indicators for CAD presence and severity. Patients admitted to the Department of Cardiology who underwent coronary angiography were included. This resulted in an inclusion of 212 patients, of which 73 had no CAD. During the same visit, 6 × 6-mm (nominal size) fovea-centered optical coherence tomography angiography images of both eyes were acquired. The Gensini score (GS) was utilized to quantify CAD severity. Six known FAZ shape metrics were assessed and three novel biomarkers based on the inner ellipse were defined: absolute inner ellipse difference, Hausdorff distance, and Chamfer distance. Eight out of nine metrics showed significant associations with the GS in the left eye. However, significant differences across three CAD severity groups were only demonstrated by the novel metrics. Utilizing the Chamfer distance, age, and sex, patients with and without CAD could be distinguished with an average area under the curve (AUC) of 0.89 (95% confidence interval [CI], 0.84-0.95). Moreover, three CAD severity groups could be discerned with a macro average AUC of 0.77 (95% CI, 0.72-0.84). A comprehensive assessment of FAZ shape descriptors was performed, and a strong association with CAD was found. The inner ellipse-based biomarkers especially demonstrated high predictive abilities for CAD presence and severity.

3-D Brain Reconstruction by Hierarchical Shape-Perception Network From a Single Incomplete Image.

3-D shape reconstruction is essential in the navigation of minimally invasive and auto robot-guided surgeries whose operating environments are indirect and narrow, and there have been some works that focused on reconstructing the 3-D shape of the surgical organ through limited 2-D information available. However, the lack and incompleteness of such information caused by intraoperative emergencies (such as bleeding) and risk control conditions have not been considered. In this article, a novel hierarchical shape-perception network (HSPN) is proposed to reconstruct the 3-D point clouds (PCs) of specific brains from one single incomplete image with low latency. A branching predictor and several hierarchical attention pipelines are constructed to generate PCs that accurately describe the incomplete images and then complete these PCs with high quality. Meanwhile, attention gate blocks (AGBs) are designed to efficiently aggregate geometric local features of incomplete PCs transmitted by hierarchical attention pipelines and internal features of reconstructing PCs. With the proposed HSPN, 3-D shape perception and completion can be achieved spontaneously. Comprehensive results measured by Chamfer distance (CD) and PC-to-PC error demonstrate that the performance of the proposed HSPN outperforms other competitive methods in terms of qualitative displays, quantitative experiment, and classification evaluation.

Advanced 3D Face Reconstruction from Single 2D Images Using Enhanced Adversarial Neural Networks and Graph Neural Networks.

This paper presents a novel framework for 3D face reconstruction from single 2D images and addresses critical limitations in existing methods. Our approach integrates modified adversarial neural networks with graph neural networks to achieve state-of-the-art performance. Key innovations include (1) a generator architecture based on Graph Convolutional Networks (GCNs) with a novel loss function and identity blocks, mitigating mode collapse and instability; (2) the integration of facial landmarks and a non-parametric efficient-net decoder for enhanced feature capture; and (3) a lightweight GCN-based discriminator for improved accuracy and stability. Evaluated on the 300W-LP and AFLW2000-3D datasets, our method outperforms existing approaches, reducing Chamfer Distance by 62.7% and Earth Mover's Distance by 57.1% on 300W-LP. Moreover, our framework demonstrates superior robustness to variations in head positioning, occlusion, noise, and lighting conditions while achieving significantly faster processing times.

PesRec: A parametric estimation method for indoor semantic scene reconstruction from a single image

Reconstructing semantic indoor scenes is a challenging task in augmented and virtual reality. The quality of scene reconstruction is limited by the complexity and occlusion of indoor scenes. This is due to the difficulty in estimating the spatial structure of the scene and insufficient learning for object location inference. To address these challenges, we have developed PesRec, an end-to-end multi-task scene reconstruction network for parameterizing indoor semantic information. PesRec incorporates a newly designed spatial layout estimator and a 3D object detector to effectively learn scene parameter features from RGB images. We modify an object mesh generator to enhance the robustness of reconstructing indoor occluded objects through point cloud optimization in PesRec. Using the analyzed scene parameters and spatial structure, the proposed PesRec reconstructs an indoor scene by placing object meshes scaled to 3D detection boxes in an estimated layout cuboid. Extensive experiments on two benchmark datasets demonstrate that PesRec performs exceptionally well for object reconstruction with an average chamfer distance of 5.24 × 10-3 on the Pix3D dataset including 53.61 % mAP for 3D object detection and 79.7 % 3D IoU for the estimation of layout on the commonly-used SUN RGB-D datasets. The proposed computing network breaks through the limitations caused by complex indoor scenes and occlusions, showing optimization results that improve the quality of reconstruction in the fields of augmented reality and virtual reality.

Balanced parametric body prior for implicit clothed human reconstruction from a monocular RGB

AbstractThe authors study the problem of reconstructing detailed 3D human surfaces in various poses and clothing from images. The parametric human body allows accurate 3D clothed human reconstruction. However, the offset of large and loose clothing from the inferred parametric body mesh confines the generalisation of the existing parametric body‐based methods. A distinctive method that simultaneously generalises well to unseen poses and unseen clothing is proposed. The authors first discover the unbalanced nature of existing implicit function‐based methods. To address this issue, the authors propose to synthesise the balanced training samples with a new dependency coefficient in training. The dependency coefficient can tell the network whether the prior from the parametric body model is reliable. The authors then design a novel positional embedding‐based attenuation strategy to incorporate the dependency coefficient into the implicit function (IF) network. Comprehensive experiments are conducted on the CAPE dataset to study the effectiveness of the authors’ approach. The proposed method significantly surpasses state‐of‐the‐art approaches and generalises well on unseen poses and clothing. As an illustrative example, the proposed method improves the Chamfer Distance Error and Normal Error by 38.2% and 57.6%.

3D point cloud reconstruction for array GM-APD lidar based on echo waveform decomposition

Array GM-APD lidar only reconstructs one response distance per pixel, resulting in 3D point clouds sparse. This paper proposes a 3D point cloud reconstruction algorithm using echo waveforms directly. First, combining empirical mode decomposition and the array GM-APD lidar echo waveform characteristics to extract multiple target response distances per pixel. Then, assuming per-pixel target surface rotation to resolve the shared azimuth and polar angles of multiple response distances. Calculate the rotation angles using the decomposed distance difference and by minimizing the plane fitting error. Finally, reconstruct the 3D point cloud by rotation translation transformation. Simulations and experiments demonstrate that the proposed algorithm reduces the Chamfer Distance of the reconstructed 3D point cloud by over 10 % compared to the original. The reconstructed 3D point cloud of buildings and vehicles shows lower sparsity and stepwise, and the reconstructed 3D point cloud for each target in the multiple-target scene is unaffected by others.

Super-Resolution Virtual Scene Rendering Technology Based on Generalized Huber-MRF Image Modeling

The traditional rendering technology creates virtual scenes with insufficient fidelity, which are quite different from real scenes. To address this issue, a super-resolution virtual scene rendering technology based on generalized Huber-MRF image modeling has been studied. This study preprocesses the original image through three steps: graying, filtering, and enhancement. The generalized Huber-MRF is employed for super-resolution image restoration to enhance image clarity. Corner features are extracted from the super-resolution image, and the Delaunay triangular grid method is used to construct the image's 3D model. Texture and lighting conditions of the virtual scene are then set through texture mapping, shadow rendering, and other technologies to achieve realistic scene effects. The results indicate that, when applied, the research technology yields a relatively small chamfer distance in virtual scene modeling, suggesting that the design method preserves the details and shape information of the original image, reducing the difference between the virtual scene and the real scene and increasing the fidelity of the virtual scene. Furthermore, this method achieves maximum PSNR and SSIM values of 17.54 and 0.978, respectively, with an image preprocessing time of only 1.21 s and a CPU utilization rate of only 35.5%. This method demonstrates excellent performance across multiple aspects.

Automatic 3D Teeth Reconstruction From Five Intra-Oral Photos Using Parametric Teeth Model.

Orthodontic treatment is a lengthy process that requires regular in-person dental monitoring, making remote dental monitoring a viable alternative when face-to-face consultation is not possible. In this study, we propose an improved 3D teeth reconstruction framework that automatically restores the shape, arrangement, and dental occlusion of upper and lower teeth from five intra-oral photographs to aid orthodontists in visualizing the condition of patients in virtual consultations. The framework comprises a parametric model that leverages statistical shape modeling to describe the shape and arrangement of teeth, a modified U-net that extracts teeth contours from intra-oral images, and an iterative process that alternates between finding point correspondences and optimizing a compound loss function to fit the parametric teeth model to predicted teeth contours. We perform a five-fold cross-validation on a dataset of 95 orthodontic cases and report an average Chamfer distance of 1.0121 mm2 and an average Dice similarity coefficient of 0.7672 on all the test samples in the cross-validation, demonstrating a significant improvement compared with the previous work. Our teeth reconstruction framework provides a feasible solution for visualizing 3D teeth models in remote orthodontic consultations.

Deformation Estimation of Textureless Objects from a Single Image.

Deformations introduced during the production of plastic components degrade the accuracy of their 3D geometric information, a critical aspect of object inspection processes. This phenomenon is prevalent among primary plastic products from manufacturers. This work proposes a solution for the deformation estimation of textureless plastic objects using only a single RGB image. This solution encompasses a unique image dataset of five deformed parts, a novel method for generating mesh labels, sequential deformation, and a training model based on graph convolution. The proposed sequential deformation method outperforms the prevalent chamfer distance algorithm in generating precise mesh labels. The training model projects object vertices into features extracted from the input image, and then, predicts vertex location offsets based on the projected features. The predicted meshes using these offsets achieve a sub-millimeter accuracy on synthetic images and approximately 2.0 mm on real images.

Patient-specific reference model estimation for orthognathic surgical planning.

Accurate estimation of reference bony shape models is fundamental for orthognathic surgical planning. Existing methods to derive this model are of two types: one determines the reference model by estimating the deformation field to correct the patient's deformed jaw, often introducing distortions in the predicted reference model; The other derives the reference model using a linear combination of their landmarks/vertices but overlooks the intricate nonlinear relationship between the subjects, compromising the model's precision and quality. We have created a self-supervised learning framework to estimate the reference model. The core of this framework is a deep query network, which estimates the similarity scores between the patient's midface and those of the normal subjects in a high-dimensional space. Subsequently, it aggregates high-dimensional features of these subjects and projects these features back to 3D structures, ultimately achieving a patient-specific reference model. Our approach was trained using a dataset of 51 normal subjects and tested on 30 patient subjects to estimate their reference models. Performance assessment against the actual post-operative bone revealed a mean Chamfer distance error of 2.25 mm and an average surface distance error of 2.30 mm across the patient subjects. Our proposed method emphasizes the correlation between the patients and the normal subjects in a high-dimensional space, facilitating the generation of the patient-specific reference model. Both qualitative and quantitative results demonstrate its superiority over current state-of-the-art methods in reference model estimation.

HoloGS: Instant Depth-based 3D Gaussian Splatting with Microsoft HoloLens 2

Abstract. In the fields of photogrammetry, computer vision and computer graphics, the task of neural 3D scene reconstruction has led to the exploration of various techniques. Among these, 3D Gaussian Splatting stands out for its explicit representation of scenes using 3D Gaussians, making it appealing for tasks like 3D point cloud extraction and surface reconstruction. Motivated by its potential, we address the domain of 3D scene reconstruction, aiming to leverage the capabilities of the Microsoft HoloLens 2 for instant 3D Gaussian Splatting. We present HoloGS, a novel workflow utilizing HoloLens sensor data, which bypasses the need for pre-processing steps like Structure from Motion by instantly accessing the required input data i.e. the images, camera poses and the point cloud from depth sensing. We provide comprehensive investigations, including the training process and the rendering quality, assessed through the Peak Signal-to-Noise Ratio, and the geometric 3D accuracy of the densified point cloud from Gaussian centers, measured by Chamfer Distance. We evaluate our approach on two self-captured scenes: An outdoor scene of a cultural heritage statue and an indoor scene of a fine-structured plant. Our results show that the HoloLens data, including RGB images, corresponding camera poses, and depth sensing based point clouds to initialize the Gaussians, are suitable as input for 3D Gaussian Splatting.

Shape completion in the dark: completing vertebrae morphology from 3D ultrasound

PurposeUltrasound (US) imaging, while advantageous for its radiation-free nature, is challenging to interpret due to only partially visible organs and a lack of complete 3D information. While performing US-based diagnosis or investigation, medical professionals therefore create a mental map of the 3D anatomy. In this work, we aim to replicate this process and enhance the visual representation of anatomical structures.MethodsWe introduce a point cloud-based probabilistic deep learning (DL) method to complete occluded anatomical structures through 3D shape completion and choose US-based spine examinations as our application. To enable training, we generate synthetic 3D representations of partially occluded spinal views by mimicking US physics and accounting for inherent artifacts.ResultsThe proposed model performs consistently on synthetic and patient data, with mean and median differences of 2.02 and 0.03 in Chamfer Distance (CD), respectively. Our ablation study demonstrates the importance of US physics-based data generation, reflected in the large mean and median difference of 11.8 CD and 9.55 CD, respectively. Additionally, we demonstrate that anatomical landmarks, such as the spinous process (with reconstruction CD of 4.73) and the facet joints (mean distance to ground truth (GT) of 4.96 mm), are preserved in the 3D completion.ConclusionOur work establishes the feasibility of 3D shape completion for lumbar vertebrae, ensuring the preservation of level-wise characteristics and successful generalization from synthetic to real data. The incorporation of US physics contributes to more accurate patient data completions. Notably, our method preserves essential anatomical landmarks and reconstructs crucial injections sites at their correct locations.

Evaluate Geometry of Radiance Fields with Low-Frequency Color Prior

A radiance field is an effective representation of 3D scenes, which has been widely adopted in novel-view synthesis and 3D reconstruction. It is still an open and challenging problem to evaluate the geometry, i.e., the density field, as the ground-truth is almost impossible to obtain. One alternative indirect solution is to transform the density field into a point-cloud and compute its Chamfer Distance with the scanned ground-truth. However, many widely-used datasets have no point-cloud ground-truth since the scanning process along with the equipment is expensive and complicated. To this end, we propose a novel metric, named Inverse Mean Residual Color (IMRC), which can evaluate the geometry only with the observation images. Our key insight is that the better the geometry, the lower-frequency the computed color field. From this insight, given a reconstructed density field and observation images, we design a closed-form method to approximate the color field with low-frequency spherical harmonics, and compute the inverse mean residual color. Then the higher the IMRC, the better the geometry. Qualitative and quantitative experimental results verify the effectiveness of our proposed IMRC metric. We also benchmark several state-of-the-art methods using IMRC to promote future related research. Our code is available at https://github.com/qihangGH/IMRC.

LISR: Learning Linear 3D Implicit Surface Representation Using Compactly Supported Radial Basis Functions

Implicit 3D surface reconstruction of an object from its partial and noisy 3D point cloud scan is the classical geometry processing and 3D computer vision problem. In the literature, various 3D shape representations have been developed, differing in memory efficiency and shape retrieval effectiveness, such as volumetric, parametric, and implicit surfaces. Radial basis functions provide memory-efficient parameterization of the implicit surface. However, we show that training a neural network using the mean squared error between the ground-truth implicit surface and the linear basis-based implicit surfaces does not converge to the global solution. In this work, we propose locally supported compact radial basis functions for a linear representation of the implicit surface. This representation enables us to generate 3D shapes with arbitrary topologies at any resolution due to their continuous nature. We then propose a neural network architecture for learning the linear implicit shape representation of the 3D surface of an object. We learn linear implicit shapes within a supervised learning framework using ground truth Signed-Distance Field (SDF) data for guidance. The classical strategies face difficulties in finding linear implicit shapes from a given 3D point cloud due to numerical issues (requires solving inverse of a large matrix) in basis and query point selection. The proposed approach achieves better Chamfer distance and comparable F-score than the state-of-the-art approach on the benchmark dataset. We also show the effectiveness of the proposed approach by using it for the 3D shape completion task.

Learning Spatially Collaged Fourier Bases for Implicit Neural Representation

Existing approaches to Implicit Neural Representation (INR) can be interpreted as a global scene representation via a linear combination of Fourier bases of different frequencies. However, such universal basis functions can limit the representation capability in local regions where a specific component is unnecessary, resulting in unpleasant artifacts. To this end, we introduce a learnable spatial mask that effectively dispatches distinct Fourier bases into respective regions. This translates into collaging Fourier patches, thus enabling an accurate representation of complex signals. Comprehensive experiments demonstrate the superior reconstruction quality of the proposed approach over existing baselines across various INR tasks, including image fitting, video representation, and 3D shape representation. Our method outperforms all other baselines, improving the image fitting PSNR by over 3dB and 3D reconstruction to 98.81 IoU and 0.0011 Chamfer Distance.

Self-Supervised Bird’s Eye View Motion Prediction with Cross-Modality Signals

Learning the dense bird's eye view (BEV) motion flow in a self-supervised manner is an emerging research for robotics and autonomous driving. Current self-supervised methods mainly rely on point correspondences between point clouds, which may introduce the problems of fake flow and inconsistency, hindering the model’s ability to learn accurate and realistic motion. In this paper, we introduce a novel cross-modality self-supervised training framework that effectively addresses these issues by leveraging multi-modality data to obtain supervision signals. We design three innovative supervision signals to preserve the inherent properties of scene motion, including the masked Chamfer distance loss, the piecewise rigidity loss, and the temporal consistency loss. Through extensive experiments, we demonstrate that our proposed self-supervised framework outperforms all previous self-supervision methods for the motion prediction task.

Point Cloud Completion Based on Nonlocal Neural Networks with Adaptive Sampling

Raw point clouds are usually sparse and incomplete, inevitably containing outliers or noise from 3D sensors. In this paper, an improved SA-Net based on an encoder-decoder structure is proposed to make it more robust in predicting complete point clouds. The encoder of the original SA-Net network is very sensitive to noise in the feature extraction process. Therefore, we use PointASNL as the encoder, which weights around the initial sampling points through the AS module (Adaptive Sampling Module) and adaptively adjusts the weight of the sampling points to effectively alleviate the bias effect of outliers. In order to fully mine the feature information of point clouds, it captures the neighborhood and long-distance dependencies of sampling points through the LNL module (Local-NonLocal Module), providing more accurate information for point cloud processing. Then, we use the encoder to extract local geometric features of the incomplete point cloud at different resolutions.Then, an attention mechanism is introduced to transfer the extracted features to a decoder. The decoder gradually refines the local features to achieve a more realistic effect. Experiments on the ShapeNet data set show that the improved point cloud completion network achieves the goal and reduces the average chamfer distance by 3.50% compared to SA-Net.

A point contextual transformer network for point cloud completion

Point cloud completion is an essential task for recovering a complete point cloud from its partial observation to support downstream applications, such as object detection and reconstruction. Existing point cloud completion networks primarily rely on large-scale datasets to learn the mapping between the partial shapes and the complete shapes. They often adopt a multi-stage strategy to progressively generate complete point clouds with finer details. However, underutilization of shape priors and complex modelling frameworks still plague these networks. To address these issues, we innovatively propose a point contextual transformer (PCoT) for point cloud completion (PCoT-Net). We design the PCoT to adaptively fuse static and dynamic point contextual information. This allows for the effective capture of fine-grained local contextual features. We then propose a one-stage network with a feature completion module to directly generate credible and detailed complete point cloud results. Furthermore, we incorporate External Attention (EA) into the feature completion module, which is lightweight and further improves the performance of learning complete features and reconstructing the complete point cloud. Extensive experiments on various datasets validate the effectiveness of our PCoT-based approach and the EA-enhanced feature completion module, which achieves superior quantitative performance in Chamfer Distance (CD) and F1-Score. In comparison to PMP-Net++ (Wen et al., 2022), our method improves the F1-Score by 0.010, 0.022, and 0.026, and reduces the CD by 0.16, 0.95, and 1.74 on the MVP, CRN, and ScanNet datasets, respectively, while providing visually superior results, capturing more fine-grained details and producing smoother reconstructed surfaces.

The application of gaming virtual scenarios generated by point cloud 3D in inducing psychological intervention

With the development of science and technology, virtual reality and other technologies have gradually developed and popularized, sprouting a series of interdisciplinary, such as evaluation and intervention in the psychological Affective computing. To enhance the realism of virtual situational materials for psychological intervention, this study proposed the application of point cloud 3D generated gameplay virtual scenarios in induced psychological intervention. It utilized the Kneading Net model to construct a point cloud 3D generation deep learning network, and combined style transfer algorithm to construct an emotion induced monomer model. Finally, the complete scene was constructed using the key technology of the positive feedback psychological emotion induced scene production system. The experimental data showed that when the three modules of cube cavity template, geometric feature and dynamic chamfer distance in the Kneading Net model were used meanwhile, the common chamfer distance was 0.0240, which was 0.0003 lower than the original network. This indicated that the simultaneous use of the three modules can achieve optimal network performance and can be applied in scenarios with high accuracy requirements. The comprehensive scores of scene realism and immersion were 6.93 and 7.4, respectively, both higher than 6.5. This indicates that the induced psychological intervention effect of the gameplay virtual environment generated by point cloud 3D meets the design expectations. This helps to enhance the user’s sense of experience and enhance the positive effect of psychological intervention.

3D Reconstruction of Wheat Plants by Integrating Point Cloud Data and Virtual Design Optimization

The morphology and structure of wheat plants are intricate, containing numerous tillers, rich details, and significant cross-obscuration. Methods of effectively reconstructing three-dimensional (3D) models of wheat plants that reflects the varietal architectural differences using measured data is challenging in plant phenomics and functional–structural plant models. This paper proposes a 3D reconstruction technique for wheat plants that integrates point cloud data and virtual design optimization. The approach extracted single stem number, growth position, length, and inclination angle from the point cloud data of a wheat plant. It then built an initial 3D mesh model of the plant by integrating a wheat 3D phytomer template database with variety resolution. Diverse 3D wheat plant models were subsequently virtually designed by iteratively modifying the leaf azimuth, based on the initial model. Using the 3D point cloud of the plant as the overall constraint and setting the minimum Chamfer distance between the point cloud and the mesh model as the optimization objective, we obtained the optimal 3D model as the reconstruction result of the plant through continuous iterative calculation. The method was validated using 27 winter wheat plants, with nine varieties and three replicates each. The R2 values between the measured data and the reconstructed plants were 0.80, 0.73, 0.90, and 0.69 for plant height, crown width, plant leaf area, and coverage, respectively. Additionally, the Normalized Root Mean Squared Errors (NRMSEs) were 0.10, 0.12, 0.08, and 0.17, respectively. The Mean Absolute Percentage Errors (MAPEs) used to investigate the vertical spatial distribution between the reconstructed 3D models and the point clouds of the plants ranged from 4.95% to 17.90%. These results demonstrate that the reconstructed 3D model exhibits satisfactory consistency with the measured data, including plant phenotype and vertical spatial distribution, and accurately reflects the characteristics of plant architecture and spatial distribution for the utilized wheat cultivars. This method provides technical support for research on wheat plant phenotyping and functional–structural analysis.