Related papers: End-to-end Learning of Cost-Volume Aggregation for…
This paper proposes a novel meta-learning approach to optimize a robust portfolio ensemble. The method uses a deep generative model to generate diverse and high-quality sub-portfolios combined to form the ensemble portfolio. The generative…
Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems. State-of-the-art stereo matching methods based on convolutional neural networks…
Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms.…
A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…
Despite the remarkable progress of deep learning in stereo matching, there exists a gap in accuracy between real-time models and slower state-of-the-art models which are suitable for practical applications. This paper presents an iterative…
Stereo depth estimation is a fundamental component in augmented reality (AR), which requires low latency for real-time processing. However, preprocessing such as rectification and non-ML computations such as cost volume require significant…
Evaluating modern machine learning models has become prohibitively expensive. Benchmarks such as LMMs-Eval and HELM demand thousands of GPU hours per model. Costly evaluation reduces inclusivity, slows the cycle of innovation, and worsens…
The core of Multi-view Stereo(MVS) is the matching process among reference and source pixels. Cost aggregation plays a significant role in this process, while previous methods focus on handling it via CNNs. This may inherit the natural…
Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. However, deep learning algorithms are sensitive to input data, and…
This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition. Given a deep multi-view stereo network, our…
Various architectures (such as GoogLeNets, ResNets, and DenseNets) have been proposed. However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters. To handle these…
Although remarkable progress has been made on single image super-resolution due to the revival of deep convolutional neural networks, deep learning methods are confronted with the challenges of computation and memory consumption in…
We present a novel end-to-end deep learning-based adaptation control algorithm for frequency-domain adaptive system identification. The proposed method exploits a deep neural network to map observed signal features to corresponding…
Nowadays, denoising diffusion probabilistic models have been adapted for many image segmentation tasks. However, existing end-to-end models have already demonstrated remarkable capabilities. Rather than using denoising diffusion…
Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent…
Monocular depth estimation is a challenging task in complex compositions depicting multiple objects of diverse scales. Albeit the recent great progress thanks to the deep convolutional neural networks (CNNs), the state-of-the-art monocular…
While most scene flow methods use either variational optimization or a strong rigid motion assumption, we show for the first time that scene flow can also be estimated by dense interpolation of sparse matches. To this end, we find sparse…
Unlike other vision tasks where Transformer-based approaches are becoming increasingly common, stereo depth estimation is still dominated by convolution-based approaches. This is mainly due to the limited availability of real-world ground…
In stereo vision, self-similar or bland regions can make it difficult to match patches between two images. Active stereo-based methods mitigate this problem by projecting a pseudo-random pattern on the scene so that each patch of an image…
Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also…