DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
A GMM-based method generates new 3D structures from medical images.
problem Generating new medical images from limited data and different modalities.
method Gaussian Mixture Model (GMM) for point-cloud generation.
result Generated point-clouds closely match training samples from the same class.
Proposes a model to generate 3D-aware images from 2D images.
problem Generating 3D-aware images from 2D images.
method Likelihood-based top-down model using Neural Radiance Fields and energy-based latent variables.
result Model can infer 3D object structures from 2D images and generate novel views.
BPI models 2D patterns on multiple planes and 3D scene from a single image.
problem Understanding and editing images with multiple 2D planes and 3D scene from a single image.
method Box Program Induction (BPI) with neural networks and search-based algorithm.
result Holistic, structured scene representation enables 3D-aware image editing.
Pix2Shape learns 3D scene representations from single images without supervision.
problem Learning 3D scene information from a single image without supervision.
method Pix2Shape uses an encoder, decoder, and critic network to generate 2.5D surfel-based reconstructions.
result Pix2Shape can generate complex 3D scenes from a single image, scaling with on-screen resolution.
StyleNeRF generates high-resolution images with 3D consistency and style control.
problem Generating high-resolution images with fine details and 3D consistency.
method Integrates NeRF into a style-based generator for efficient high-resolution image synthesis.
result Synthesizes high-resolution images at interactive rates with high 3D consistency and style control.
Paper tackles unsupervised learning of 3D shapes from single images.
problem Learning 3D shapes from single images without supervision.
method Generative models, variational auto-encoders, adversarial methods.
result Model learns 3D shapes and poses from single images, showing potential for various datasets.
Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new generative model, Visual Object Networks (VON), synthesizing natural images of o…
New method reconstructs 3D shapes from 2D images using Kendall's shape space.
problem Reconstruct 3D shapes from 2D images, especially for rare specimens.
method Kendall's shape space approach with prior information.
result More robust and plausible shapes compared to previous methods.
3D shape instantiation which reconstructs the 3D shape of a target from limited 2D images or projections is an emerging technique for surgical intervention. It improves the currently less-informative and insufficient 2D navigation schemes for robot-assisted Minimally Invasive Surgery (MIS) to 3D navigation. Previously,…
One of the challenges of using machine learning techniques with medical data is the frequent dearth of source image data on which to train. A representative example is automated lung cancer diagnosis, where nodule images need to be classified as suspicious or benign. In this work we propose an automatic synthetic lung …
A machine learning method predicts rock permeability from 3D images.
problem Efficiently predict permeability of heterogeneous rocks for planetary and robotic applications.
method Machine learning guided 3D properties recognition of rock morphology from 3D micro CT and MRI images.
result The morphology decoder method accurately predicts permeability from 3D images.
In this paper, a neural architecture search (NAS) framework is proposed for 3D medical image segmentation, to automatically optimize a neural architecture from a large design space. Our NAS framework searches the structure of each layer including neural connectivities and operation types in both of the encoder and deco…
A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods…
Deep-learning method estimates bone 3D structure from X-ray images.
problem Estimating bone 3D structure from X-ray images.
method Triplet loss-trained neural network selecting closest 3D bone shape from predefined set.
result Average RMS distance of 1.08 mm between predicted and true shapes.
A new rotation invariant method for 3D medical imaging classification.
problem Computational expense and lack of rotation invariance in 3D medical image processing.
method Proposes a rotation invariant convolution operator using hypersphere topology.
result Demonstrates improved classification accuracy and rotation invariance.
This work generates synthetic 3D thermal facial data using 2D facial data and deep learning.
problem Creating large datasets for deep learning in computer vision.
method 3D facial modelling techniques and deep learning methodologies.
result Synthetic 3D thermal facial data created for deep learning applications.
Proposes a method to improve skull stripping accuracy in MRI images.
problem Skull stripping accuracy in MRI images is improved.
method Context-encoding method to empower 2D networks with 3D semantic information.
result Achieves superior accuracy (dice score 99.6% on NFBS, 99.09% on LPBA40, 99.17% on OASIS) compared to state-of-the-art methods.
Worldsheet wraps a 3D mesh sheet onto a single image to synthesize novel views.
problem Synthesizing novel views from a single image with large viewpoint changes.
method Shrink-wrapping a planar mesh sheet onto the input image, consistent with learned depth.
result Worldsheet consistently outperforms prior methods on single-image view synthesis.
DISPR uses diffusion models to predict 3D cell shapes from 2D images.
problem Predicting 3D cell shapes from 2D microscopy images.
method Diffusion model trained to predict 3D shapes from 2D microscopy images as a prior.
result Adding DISPR predictions to minority cell classes improves classification accuracy.
3D adversarial logos can fool object detectors in real-world settings.
problem Creating robust adversarial attacks in 3D rendering views.
method Constructing 3D adversarial logos via texture mapping and differentiable rendering.
result 3D adversarial logos are more versatile and robust than traditional adversarial patches.
Study evaluates using multiple slices as input for CNNs in medical image segmentation.
problem Improving segmentation performance in medical images with limited computational resources.
method Compared pseudo-3D and 2D approaches using different CNN architectures and datasets.
result Multi-slice inputs did not significantly improve segmentation performance over 2D or 3D CNNs.
3D object classification and segmentation using deep neural networks has been extremely successful. As the problem of identifying 3D objects has many safety-critical applications, the neural networks have to be robust against adversarial changes to the input data set. There is a growing body of research on generating h…
In this work we propose an adversarial learning approach to generate high resolution MRI scans from low resolution images. The architecture, based on the SRGAN model, adopts 3D convolutions to exploit volumetric information. For the discriminator, the adversarial loss uses least squares in order to stabilize the traini…
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional latent scenes, due to challenges in both modeling and inference. Accounting for th…
Deep neural network models used for medical image segmentation are large because they are trained with high-resolution three-dimensional (3D) images. Graphics processing units (GPUs) are widely used to accelerate the trainings. However, the memory on a GPU is not large enough to train the models. A popular approach to …
ObSuRF converts a single image into a 3D model with NeRFs.
problem Creating a 3D model from a single image with object segmentation.
method Unsupervised volume segmentation using Neural Radiance Fields (NeRFs).
result ObSuRF can segment a 3D scene into objects from a single image.
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manne…
3D ConvNets improved with Project & Excite for medical imaging segmentation.
problem Improving segmentation performance in 3D medical imaging.
method Proposed Project & Excite (PE) modules for 3D F-CNNs, extending 2D recalibration methods.
result Project & Excite modules boost segmentation performance up to 0.3 in Dice Score.
The paper proposes a method to learn 3D object pose manifolds using GANs and elasticae.
problem Learning image manifolds of 3D objects with limited data.
method Geom-SGAN and elasticae for geometry-preserving image interpolation.
result The method outperforms state-of-the-art GANs and VAEs in learning rotation paths.
Tab2vox converts tabular data into 3D images for improved demand forecasting.
problem Forecasting demand influenced by multi-level causes and large volatility.
method Tab2vox neural architecture search (NAS) model to convert tabular data into 3D voxel images for 3D CNN forecasting.
result 3D CNN forecasting model outperforms existing tabular data techniques.
Topology-enhanced loss improves 3D object reconstruction from 2D images.
problem Challenges in reconstructing 3D objects from 2D images, especially capturing shape information.
method Integrates multi-scale topological features into the reconstruction loss using cubical complexes and optimal transport distance.
result Topology-aware loss substantially improves 3D reconstruction quality.
NeRF-VAE generates 3D scenes with geometric structure from few images.
problem Generating 3D scenes from few images with geometric consistency.
method Combines NeRF and VAE, incorporating shared geometric structure.
result NeRF-VAE can infer and render geometrically-consistent scenes from unseen environments.
ED-NeRF efficiently edits 3D scenes using latent space NeRF and improved loss functions.
problem Slow training speeds and inadequate editing loss functions in existing NeRF editing techniques.
method Embedding real-world scenes into latent space of LDM, using a unique refinement layer and an improved loss function.
result ED-NeRF achieves faster editing speed and improved output quality compared to state-of-the-art models.
Enhances 2D face recognition with 3D features using active illumination.
problem Improving robustness of 2D face recognition to spoofing attacks and low-light conditions.
method Projecting a high spatial frequency pattern onto the face to recover 3D information and a 2D image simultaneously.
result Significantly boosts face recognition performance and dramatically improves robustness to spoofing attacks.
Large prospective epidemiological studies acquire cardiovascular magnetic resonance (CMR) images for pre-symptomatic populations and follow these over time. To support this approach, fully automatic large-scale 3D analysis is essential. In this work, we propose a novel deep neural network using both CMR images and pati…
Generates garden paintings from text descriptions using deep learning.
problem Lack of firsthand material for traditional Chinese garden reconstruction.
method Deep learning model trained on text and paintings of Ming Dynasty gardens.
result Model generates garden paintings in Ming Dynasty style based on textual descriptions.
Deep learning improves 3D microscopy resolution without matched target images.
problem Anisotropic resolution in volumetric fluorescence microscopy.
method Cycle-consistent generative adversarial network trained on unpaired 2D images.
result Enhanced axial resolution and restored details between imaging planes.
Paper extends 2D ZSAD to 3D MRI without training, achieving robust anomaly detection.
problem Challenges in extending zero-shot anomaly detection to 3D medical images.
method Constructs localized volumetric tokens by aggregating 2D slices processed by 2D foundation models.
result Training-free, batch-based ZSAD effectively extends from 2D encoders to full 3D MRI volumes.
Paper uses VAEs and GANs to estimate cryo-EM image orientation and camera parameters.
problem Estimating orientation and camera parameters from noisy cryo-EM images.
method Combines VAEs and GANs to learn latent representation, then designs estimation method.
result Geometric approach for fast cryo-EM biomolecule reconstruction.
3D CNNs interpret brain MRI differences between men and women.
problem Interpreting 3D CNNs for voxel-wise brain MRI analysis.
method Three interpretation methods: Meaningful Perturbations, Grad CAM, and Guided Backpropagation.
result Voxel-wise 3D CNN interpretation of brain MRI data.
3D CNN accurately classifies infant neurodevelopmental age from MRI scans.
problem Estimating neurodevelopmental age in infants from MRI data.
method 3D Convolutional Neural Network (3D CNN) trained on MRI images of 112 infants.
result 3D CNN achieves 99% sensitivity and 98.3% specificity in age classification.
Medical image registration is one of the key processing steps for biomedical image analysis such as cancer diagnosis. Recently, deep learning based supervised and unsupervised image registration methods have been extensively studied due to its excellent performance in spite of ultra-fast computational time compared to …
Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation pipeline requires numerous design decisions such as the selection of 3D shapes and …
The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and the design of accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition…
Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and therefore, end-to-end training is limited by GPU memory and data size. To overcome this issue, we introduce a netwo…
Predict steering angles of self-driving cars from images.
problem Predicting steering angles for self-driving cars using image data.
method Used deep learning techniques like Transfer Learning, 3D CNN, LSTM, and ResNet to predict steering angles.
result Both models placed in the top ten of Udacity's challenge.
Characterizing statistical properties of solutions of inverse problems is essential for decision making. Bayesian inversion offers a tractable framework for this purpose, but current approaches are computationally unfeasible for most realistic imaging applications in the clinic. We introduce two novel deep learning bas…