An official website of the United States government
3D image reconstruction from a limited number of 2D images has been a long-standing challenge in computer vision and image analysis. While deep learning-based approaches have achieved impressive performance in this area, existing deep networks often fail to effectively utilize the shape structures of objects presented in images. As a result, the topology of reconstructed objects may not be well preserved, leading to the presence of artifacts such as discontinuities, holes, or mismatched connections between different parts. In this paper, we propose a shape-aware network based on diffusion models for 3D image reconstruction, named SADIR, to address these issues. In contrast to previous methods that primarily rely on spatial correlations of image intensities for 3D reconstruction, our model leverages shape priors learned from the training data to guide the reconstruction process. To achieve this, we develop a joint learning network that simultaneously learns a mean shape under deformation models. Each reconstructed image is then considered as a deformed variant of the mean shape. We validate our model, SADIR, on both brain and cardiac magnetic resonance images (MRIs). Experimental results show that our method outperforms the baselines with lower reconstruction error and better preservation of the shape structure of objects within the images.
more »
« less
Topology-Aware Single-Image 3D Shape Reconstruction
We make an attempt to address topology-awareness for 3D shape reconstruction. Two types of high-level shape typologies are being studied here, namely genus (number of cuttings/holes) and connectivity (number of connected components), which are of great importance in 3D object reconstruction/understanding but have been thus far disjoint from the existing dense voxel-wise prediction literature. We propose a topology-aware shape autoencoder component (TPWCoder) by approximating topology property functions such as genus and connectivity with neural networks from the latent variables. TPWCoder can be directly combined with the existing 3D shape reconstruction pipelines for end-to-end training and prediction. On the challenging A Big CAD Model Dataset (ABC), TPWCoder demonstrates a noticeable quantitative and qualitative improvement over the competing methods, and it also shows improved quantitative result on the ShapeNet dataset.
more »
« less
- PAR ID:
- 10166846
- Date Published:
- Journal Name:
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops
- ISSN:
- 2160-7516
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Recent advances in deep generative models have led to immense progress in 3D shape synthesis. While existing models are able to synthesize shapes represented as voxels, point-clouds, or implicit functions, these methods only indirectly enforce the plausibility of the final 3D shape surface. Here we present a 3D shape synthesis framework (SurfGen) that directly applies adversarial training to the object surface. Our approach uses a differentiable spherical projection layer to capture and represent the explicit zero isosurface of an implicit 3D generator as functions defined on the unit sphere. By processing the spherical representation of 3D object surfaces with a spherical CNN in an adversarial setting, our generator can better learn the statistics of natural shape surfaces. We evaluate our model on large-scale shape datasets, and demonstrate that the end-to-end trained model is capable of generating high fidelity 3D shapes with diverse topology.more » « less
-
Capturing document images with hand-held devices in unstructured environments is a common practice nowadays. However, “casual” photos of documents are usually unsuitable for automatic information extraction, mainly due to physical distortion of the document paper, as well as various camera positions and illumination conditions. In this work, we propose DewarpNet, a deep-learning approach for document image unwarping from a single image. Our insight is that the 3D geometry of the document not only determines the warping of its texture but also causes the illumination effects. Therefore, our novelty resides on the explicit modeling of 3D shape for document paper in an end-to-end pipeline. Also, we contribute the largest and most comprehensive dataset for document image unwarping to date – Doc3D. This dataset features multiple ground-truth annotations, including 3D shape, surface normals, UV map, albedo image, etc. Training with Doc3D, we demonstrate state-of-the-art performance for DewarpNet with extensive qualitative and quantitative evaluations. Our network also significantly improves OCR performance on captured document images, decreasing character error rate by 42% on average. Both the code and the dataset are released.more » « less
-
Quantitative volumetric assessment of filamentous actin (F‐actin) fibers remains challenging due to their interconnected nature, leading researchers to utilize threshold‐based or qualitative measurement methods with poor reproducibility. Herein, a novel machine learning‐based methodology is introduced for accurate quantification and reconstruction of nuclei‐associated F‐actin. Utilizing a convolutional neural network (CNN), actin filaments and nuclei from 3D confocal microscopy images are segmented and then each fiber is reconstructed by connecting intersecting contours on cross‐sectional slices. This allows measurement of the total number of actin filaments and individual actin filament length and volume in a reproducible fashion. Focusing on the role of F‐actin in supporting nucleocytoskeletal connectivity, apical F‐actin, basal F‐actin, and nuclear architecture in mesenchymal stem cells (MSCs) are quantified following the disruption of the linker of nucleoskeleton and cytoskeleton (LINC) complexes. Disabling LINC in MSCs generates F‐actin disorganization at the nuclear envelope characterized by shorter length and volume of actin fibers contributing a less elongated nuclear shape. The findings not only present a new tool for mechanobiology but introduce a novel pipeline for developing realistic computational models based on quantitative measures of F‐actin.more » « less
-
Identifying regions of late mechanical activation (LMA) of the left ventricular (LV) myocardium is critical in determining the optimal pacing site for cardiac resynchronization therapy in patients with heart failure. Several deep learning-based approaches have been developed to predict 3D LMA maps of LV myocardium from a stack of sparse 2D cardiac magnetic resonance imaging (MRIs). However, these models often loosely consider the geometric shape structure of the myocardium. This makes the reconstructed activation maps suboptimal; hence leading to a reduced accuracy of predicting the late activating regions of hearts. In this paper, we propose to use shape-constrained diffusion models to better reconstruct a 3D LMA map, given a limited number of 2D cardiac MRI slices. In contrast to previous methods that primarily rely on spatial correlations of image intensities for 3D reconstruction, our model leverages object shape as priors learned from the training data to guide the reconstruction process. To achieve this, we develop a joint learning network that simultaneously learns a mean shape under deformation models. Each reconstructed image is then considered as a deformed variant of the mean shape. To validate the performance of our model, we train and test the proposed framework on a publicly available mesh dataset of 3D myocardium and compare it with state-of-the-art deep learning-based reconstruction models. Experimental results show that our model achieves superior performance in reconstructing the 3D LMA maps as compared to the state-of-the-art models.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
