With dense inputs, Neural Radiance Fields (NeRF) is able to render photo-realistic novel views under static conditions. Although the synthesis quality is excellent, existing NeRF-based methods fail to obtain moderate three-dimensional (3D) structures. The novel view synthesis quality drops dramatically given sparse input due to the implicitly reconstructed inaccurate 3D-scene structure. We propose SfMNeRF, a method to better synthesize novel views as well as reconstruct the 3D-scene geometry. SfMNeRF leverages the knowledge from the self-supervised depth estimation methods to constrain the 3D-scene geometry during view synthesis training. Specifically, SfMNeRF employs the epipolar, photometric consistency, depth smoothness, and position-of-matches constraints to explicitly reconstruct the 3D-scene structure. Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time. In addition, SfMNeRF synthesizes novel sub-pixels in which the ground truth is obtained by image interpolation. This strategy enables SfMNeRF to include more samples to improve generalization performance. Experiments on two public datasets demonstrate that SfMNeRF surpasses state-of-the-art approaches. Code is available at https://github.com/XTU-PR-LAB/SfMNeRF
Deep learning models have demonstrated great potential in medical 3D imaging, but their development is limited by the expensive, large volume of annotated data required. Active learning (AL) addresses this by training a model on a subset of the most informative data samples without compromising performance. We compared different AL strategies and propose a framework that minimizes the amount of data needed for state-of-the-art performance. 638 multi-institutional brain tumor MRI images were used to train a 3D U-net model and compare AL strategies. We investigated uncertainty sampling, annotation redundancy restriction, and initial dataset selection techniques. Uncertainty estimation techniques including Bayesian estimation with dropout, bootstrapping, and margins sampling were compared to random query. Strategies to avoid annotation redundancy by removing similar images within the to-be-annotated subset were considered as well. We determined the minimum amount of data necessary to achieve similar performance to the model trained on the full dataset ({\alpha} = 0.1). A variance-based selection strategy using radiomics to identify the initial training dataset is also proposed. Bayesian approximation with dropout at training and testing showed similar results to that of the full data model with less than 20% of the training data (p=0.293) compared to random query achieving similar performance at 56.5% of the training data (p=0.814). Annotation redundancy restriction techniques achieved state-of-the-art performance at approximately 40%-50% of the training data. Radiomics dataset initialization had higher Dice with initial dataset sizes of 20 and 80 images, but improvements were not significant. In conclusion, we investigated various AL strategies with dropout uncertainty estimation achieving state-of-the-art performance with the least annotated data.
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.
The neural radiance field (NeRF) for realistic novel view synthesis requires camera poses to be pre-acquired by a structure-from-motion (SfM) approach. This two-stage strategy is not convenient to use and degrades the performance because the error in the pose extraction can propagate to the view synthesis. We integrate the pose extraction and view synthesis into a single end-to-end procedure so they can benefit from each other. For training NeRF models, only RGB images are given, without pre-known camera poses. The camera poses are obtained by the epipolar constraint in which the identical feature in different views has the same world coordinates transformed from the local camera coordinates according to the extracted poses. The epipolar constraint is jointly optimized with pixel color constraint. The poses are represented by a CNN-based deep network, whose input is the related frames. This joint optimization enables NeRF to be aware of the scene's structure that has an improved generalization performance. Extensive experiments on a variety of scenes demonstrate the effectiveness of the proposed approach. Code is available at https://github.com/XTU-PR-LAB/SaNerf.
Estimating three-dimensional human poses from the positions of two-dimensional joints has shown promising results.However, using two-dimensional joint coordinates as input loses more information than image-based approaches and results in ambiguity.In order to overcome this problem, we combine bone length and camera parameters with two-dimensional joint coordinates for input.This combination is more discriminative than the two-dimensional joint coordinates in that it can improve the accuracy of the model's prediction depth and alleviate the ambiguity that comes from projecting three-dimensional coordinates into two-dimensional space. Furthermore, we introduce direction constraints which can better measure the difference between the ground truth and the output of the proposed model. The experimental results on the H36M show that the method performed better than other state-of-the-art three-dimensional human pose estimation approaches.
Retinal image quality assessment is an essential task in the diagnosis of retinal diseases. Recently, there are emerging deep models to grade quality of retinal images. Current state-of-the-arts either directly transfer classification networks originally designed for natural images to quality classification of retinal image or introduce extra image quality priors via multiple CNN branches or independent CNNs. This paper proposes a dark and bright prior guided deep network for retinal image quality assessment called GuidedNet. Specifically, the dark and bright channel priors are embedded into the start layer of network to improve the discriminate ability of deep features. Experimental results on retinal image quality dataset Eye-Quality demonstrate the effectiveness of the proposed GuidedNet.
Segmentation of optic disc (OD) and optic cup (OC) is critical in automated fundus image analysis system. Existing state-of-the-arts focus on designing deep neural networks with one or multiple dense prediction branches. Such kind of designs ignore connections among prediction branches and their learning capacity is limited. To build connections among prediction branches, this paper introduces gradient boosting framework to deep classification model and proposes a gradient boosting network called BoostNet. Specifically, deformable side-output unit and aggregation unit with deep supervisions are proposed to learn base functions and expansion coefficients in gradient boosting framework. By stacking aggregation units in a deep-to-shallow manner, models' performances are gradually boosted along deep to shallow stages. BoostNet achieves superior results to existing deep OD and OC segmentation networks on the public dataset ORIGA.
Existing joint optic disc and cup segmentation approaches are developed either in Cartesian or polar coordinate system. However, due to the subtle optic cup, the contextual information exploited from the single domain even by the prevailing CNNs is still insufficient. In this paper, we propose a novel segmentation approach, named Cartesian-polar dual-domain network (DDNet), which for the first time considers the complementary of the Cartesian domain and the polar domain. We propose a two-branch of domain feature encoder and learn translation equivariant representations on rectilinear grid from Cartesian domain and rotation equivariant representations on polar grid from polar domain parallelly. To fuse the features on two different grids, we propose a dual-domain fusion module. This module builds the correspondence between two grids by the differentiable polar transform layer and learns the feature importance across two domains in element-wise to enhance the expressive capability. Finally, the decoder aggregates the fused features from low-level to high-level and makes dense predictions. We validate the state-of-the-art segmentation performances of our DDNet on the public dataset ORIGA. According to the segmentation masks, we estimate the commonly used clinical measure for glaucoma, i.e., the vertical cup-to-disc ratio. The low cup-to-disc ratio estimation error demonstrates the potential application in glaucoma screening.
In this paper, we propose a novel age estimation method based on GLOH feature descriptor and multi-task learning (MTL). The GLOH feature descriptor, one of the state-of-the-art feature descriptor, is used to capture the age-related local and spatial information of face image. As the exacted GLOH features are often redundant, MTL is designed to select the most informative feature bins for age estimation problem, while the corresponding weights are determined by ridge regression. This approach largely reduces the dimensions of feature, which can not only improve performance but also decrease the computational burden. Experiments on the public available FG-NET database show that the proposed method can achieve comparable performance over previous approaches while using much fewer features.
There is an increasing use of some imperceivable and redundant local features for face recognition. While only a relatively small fraction of them is relevant to the final recognition task, the feature selection is a crucial and necessary step to select the most discriminant ones to obtain a compact face representation. In this paper, we investigate the sparsity-enforced regularization-based feature selection methods and propose a multi-task feature selection method for building person specific models for face verification. We assume that the person specific models share a common subset of features and novelly reformulated the common subset selection problem as a simultaneous sparse approximation problem. To the best of our knowledge, it is the first time to apply the sparsity-enforced regularization methods for person specific face verification. The effectiveness of the proposed methods is verified with the challenging LFW face databases.