The growing demand for high-resolution, realistic rendering has significantly increased the workload for real-time path tracing, putting considerable strain on most graphics cards. One common approach to reduce the bu...
详细信息
ISBN:
(数字)9798331536626
ISBN:
(纸本)9798331536633
The growing demand for high-resolution, realistic rendering has significantly increased the workload for real-time path tracing, putting considerable strain on most graphics cards. One common approach to reduce the burden is rendering images at lower resolutions with fewer samples per pixel (spp) and then applying reconstruction techniques, such as denoising and upsampling, to achieve high-quality rendering at the desired resolution. Recovering fine details directly from noisy, low-resolution (LR) inputs in high-resolution (HR) images is challenging. There-fore, a two-stage reconstruction process is typically employed, treating denoising and upsampling as separate steps. We propose an integrated deep learning model based on a Generative Adversarial Network (GAN) to produce high-quality reconstructed images - i.e., denoised and up-sampled - for efficient, adaptive imagereconstruction. We employ a self-adaptive data augmentation strategy to iteratively reduce residual noise and recover high-frequency details, continuously improving the output. Our method significantly reduces rendering overhead while minimizing quality loss. Experimental results show consistent performance in demanding 4 x upscaling scenarios, delivering real-time performance with enhanced quality and substantial improvements.
Reconstructing an object's shape and appearance in terms of a mesh textured by a spatially-varying bidirectional reflectance distribution function (SVBRDF) from a limited set of images captured under collocated li...
详细信息
ISBN:
(数字)9798331510831
ISBN:
(纸本)9798331510848
Reconstructing an object's shape and appearance in terms of a mesh textured by a spatially-varying bidirectional reflectance distribution function (SVBRDF) from a limited set of images captured under collocated light is an ill-posed problem. Previous state-of-the-art approaches either aim to reconstruct the appearance directly on the geometry or additionally use texture normals as part of the appearance features. However, this requires detailed but inefficiently large meshes, that would have to be simplified in a post-processing step, or suffers from well-known limitations of normal maps such as missing shadows or incorrect silhouettes. Another limiting factor is the fixed and typically low resolution of the texture estimation resulting in loss of important surface details. To overcome these problems, we present ROSA, an inverse rendering method that directly optimizes mesh geometry with spatially adaptive mesh resolution solely based on the imagedata. In particular, we refine the mesh and locally condition the surface smoothness based on the estimated normal texture and mesh curvature. In addition, we enable the reconstruction of fine appearance details in high-resolution textures through a pioneering tile-based method that operates on a single pre-trained decoder network but is not limited by the network output resolution.
Lensless imaging offers a significant opportunity to develop ultra-compact cameras by removing the conventional bulky lens system. However, without a focusing element, the sensor's output is no longer a direct ima...
详细信息
ISBN:
(数字)9798331510831
ISBN:
(纸本)9798331510848
Lensless imaging offers a significant opportunity to develop ultra-compact cameras by removing the conventional bulky lens system. However, without a focusing element, the sensor's output is no longer a direct image but a complex multiplexed scene representation. Traditional methods have attempted to address this challenge by employing learnable inversions and refinement models, but these methods are primarily designed for 2D reconstruction and do not generalize well to 3D reconstruction. We introduce GANESH, a novel framework designed to enable simultaneous refinement and novel view synthesis from multi-view lensless images. Unlike existing methods that require scene-specific training, our approach supports on-the-fiy inference without retraining on each scene. Moreover, our framework allows us to tune our model to specific scenes, enhancing the rendering and refinement quality. To facilitate research in this area, we also present the first multi-view lensless dataset, LenslessScenes. Extensive experiments demonstrate that our method outperforms current approaches in reconstruction accuracy and refinement quality. Code and video results are available here.
In the era of pervasive Internet use, managing large volumes of imagedata becomes crucial. To mitigate storage and bandwidth costs, image compression plays a pivotal role. Traditional image compression techniques lik...
详细信息
ISBN:
(数字)9798331506520
ISBN:
(纸本)9798331506537
In the era of pervasive Internet use, managing large volumes of imagedata becomes crucial. To mitigate storage and bandwidth costs, image compression plays a pivotal role. Traditional image compression techniques like JPEG and PNG, while widely used, may suffer from limited compression rates. In this work, we propose a novel approach using shallow Convolutional Neural Network (CNN) autoencoders for on-the-fly image compression. Our model aims to achieve high compression rates with improved image quality compared to classical methods. Additionally, it supports decompression on the CPU in realtime, making no assumptions about client-side computational resources. We present a comprehensive methodology, including architecture design, experiments, and performance metrics. Our results demonstrate the effectiveness of the proposed approach, providing a competitive alternative for online content compression and decompression that outperforms JPEG in image quality assessment metrics at 33% compression rate. We also outperform other Learned image Compression (LIC) techniques in both the decompression time and number of trainable parameters with an improvement in the order of 10-times.
The proceedings contain 24 papers. The topics discussed include: a layered media approach to photoacoustic tomography;investigation of limited-view imagereconstruction in optoacoustic tomography employing a priori st...
ISBN:
(纸本)9780819482969
The proceedings contain 24 papers. The topics discussed include: a layered media approach to photoacoustic tomography;investigation of limited-view imagereconstruction in optoacoustic tomography employing a priori structural information;sampling rates and imagereconstructionfrom scattered fields;imposing spatio-temporal support in magnetic resonance angiographic imaging;weighted least-squares imagereconstruction in phase-contrast tomography;three-dimensional image visualization by maximum a posteriori estimation photon-counting integral imaging;in situ determination of wind fields from sailplane flight data;information theoretic characterizations of compressive-sensing-based space object identification;compressive phase contrast tomography;graphics processing unit restoration of non-uniformly warped images using a typical frame as prototype;and multiple imagereconstruction for high-resolution optical imaging using structured illumination.
imagereconstruction in various types of tomography requires inversion of the Radon transform and its generalizations. While there are many stable and robust algorithms for such inversions from reasonably well sampled...
imagereconstruction in various types of tomography requires inversion of the Radon transform and its generalizations. While there are many stable and robust algorithms for such inversions from reasonably well sampled data, most of these algo- rithms fail when applied to limited view data. In the dissertation we develop a new method of stable reconstructionfrom limited view data for functions, whose support is a union of finitely many circles. Such images, among other things, are good approx- imations of tomograms of certain types of tumors in lungs. Our method is based on a modified version of GPCA (Generalized Principal Component Analysis) and some results from algebraic geometry.
Dual-energy CT exploits the different attenuation characteristics of substances under different energy X-rays and collects high- and low-energy datafrom the same area to differentiate and quantify specific substances...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Dual-energy CT exploits the different attenuation characteristics of substances under different energy X-rays and collects high- and low-energy datafrom the same area to differentiate and quantify specific substances, which is now widely used in clinical diagnosis, disease monitoring, and other fields. If the object scanned during dual-energy CT imaging contains metallic material, the reconstructed image will suffer from metal artifacts. Metal artifacts in dual-energy CT result in surrounding tissue structures presenting erroneous CT values, blurred image details, and unclear border demarcation lines, which seriously affects the quality of the images as well as the accuracy of clinical diagnosis. To reduce metal artifacts in dual-energy CT, we combine material decomposition techniques with metal artifact reduction to explore metal artifact reduction methods applied to dual-energy CT.
Out-of-distribution (OOD) and anomaly detection are critical for reducing noise and improving the generalization of AI models in breast cancer screening, especially when handling unseen private data. Given the challen...
详细信息
ISBN:
(数字)9798331536626
ISBN:
(纸本)9798331536633
Out-of-distribution (OOD) and anomaly detection are critical for reducing noise and improving the generalization of AI models in breast cancer screening, especially when handling unseen private data. Given the challenge of limited prior knowledge about OOD samples in external unseen datasets, unsupervised generative learning is a preferable solution which trains the model to discern the normal characteristics of in-distribution (ID) data. The hypothesis is that during inference, the model aims to reconstruct ID samples accurately, while OOD samples exhibit poorer reconstruction due to their divergence from normality. In-spired by state-of-the-art (SOTA) hybrid architectures combining CNNs and transformers, we developed a novel back-bone - HAND (Hybrid ANomaly Detection), for detecting OOD from digital mammogram studies. To boost learning efficiency, we incorporated synthetic OOD samples and a parallel discriminator in the latent space to distinguish between ID and OOD samples. Gradient reversal to the OOD reconstruction loss penalizes the model for learning OOD reconstructions. An anomaly score is computed by weighting the reconstruction and the discriminator loss. On internal held-out test and external dataset, the proposed HAND model outperformed encoder-based and GAN-based baselines, and interestingly, it also outperformed the hybrid CNN+transformer baselines. Proposed HAND pipeline of-fers an automated and efficient computational solution for domain-specific quality checks in external screening mam-mograms, yielding actionable insights without direct exposure to private medical imaging data.
The primary objective of Visible-Infrared image Fusion (VIF) is to combine the rich texture and color information from visible light images with the comprehensive thermal radiation data provided by infrared images. Ho...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
The primary objective of Visible-Infrared image Fusion (VIF) is to combine the rich texture and color information from visible light images with the comprehensive thermal radiation data provided by infrared images. However, most current fusion algorithms focus solely on spatial domain feature transformations, which results in fused images lacking sufficient detail and failing to effectively preserve crucial details from the source images. In this paper, we propose Spatial-Frequency Mutual Guidance for VIF. The framework comprises two branches. Each branch reconstructs input features in the frequency and spatial domains. We introduce a novel cross-domain mutual guidance mechanism. It fully integrates information between the frequency and spatial domains to enhance the detail quality of fused images. Furthermore, a weight allocation network is utilized to adaptively assign importance to visible and infrared images based on scene characteristics. Experiments on three VIF datasets show that our method outperforms recent advanced algorithms.
Remote temperature sensing of volumetric flows has a variety of applications, such as promoting thermal comfort, heat dissipation, or data center cooling. The emergence of background-oriented schlieren (BOS) imaging i...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Remote temperature sensing of volumetric flows has a variety of applications, such as promoting thermal comfort, heat dissipation, or data center cooling. The emergence of background-oriented schlieren (BOS) imaging in recent years has enabled transparent flow visualization at minor costs. In this paper, we develop a framework for non-invasive volumetric indoor airflow estimation from a single viewpoint using BOS measurements and physics-informed reconstruction. Our framework utilizes a light projector that projects a pattern onto a target back wall and a camera that observes small distortions in the light pattern due to the change in the refractive index of the air as a result of the temperature variation. While the single-view BOS tomography problem is severely ill-posed, we regularize the reconstruction using a physics-informed neural network (PINN) that ensures that the reconstructed airflow is consistent with the coupled Boussinesq approximation of the incompressible Navier– Stokes and the heat transfer equations.
暂无评论