Related papers: Bilateral Propagation Network for Depth Completion
Distance-based attenuation is a critical aspect of wireless communications. As opposed to the ubiquitous power-law path loss model, this paper proposes a stretched exponential path loss model that is suitable for short-range communication.…
In conventional radar, the transmission of the same waveform is repeated after a predefined interval of time called pulse-repetition-interval (PRI). This technique helps to estimate the range and Doppler shift of targets and suppress…
The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable…
Recently, learning-based algorithms have shown impressive performance in underwater image enhancement. Most of them resort to training on synthetic data and achieve outstanding performance. However, these methods ignore the significant…
Kudekar et al. proved that the belief-propagation (BP) performance for low-density parity check (LDPC) codes can be boosted up to the maximum-a-posteriori (MAP) performance by spatial coupling. In this paper, spatial coupling is applied to…
In this paper, we propose a self-supervised single-view pixel-level accurate depth estimation network, called PLADE-Net. The PLADE-Net is the first work that shows unprecedented accuracy levels, exceeding 95\% in terms of the $\delta^1$…
Modern deep learning treats neural networks primarily as endpoint functions from inputs to outputs. Inspired by the shift from force to geometry in physics, we ask whether a network should instead be understood through the geometry of its…
High-precision dichotomous image segmentation (DIS) is a task of extracting fine-grained objects from high-resolution images. Existing methods trade efficiency for accuracy: non-diffusion methods are fast but suffer from weak semantics and…
In this paper, we propose an extension to the Propagator algorithm for source bearing estimation by performing root decomposition which eliminates the need for spectral search over angles. Further the propagator spatial spectrum is reused…
A ray-tracing (RT) enhanced back-projection algorithm (RT-BPA) for microwave imaging in multipath environments is presented. By tightly incorporating the concept of ray-tracing into a generalized version of traditional BPA, this method…
Belief propagation (BP) can be a useful tool to approximately contract a tensor network, provided that the contributions from any closed loops in the network are sufficiently weak. In this manuscript we describe how a loop series expansion…
Recent advances in dataset distillation have led to solutions in two main directions. The conventional batch-to-batch matching mechanism is ideal for small-scale datasets and includes bi-level optimization methods on models and syntheses,…
We introduce a dual-wavelength Fourier ptychographic topography (FPT) method that extends the lambda/2 height-range limit of single-wavelength FPT. By reconstructing complex fields at two illumination wavelengths and exploiting their phase…
To address module fragmentation, uninterpretable mappings, and deployment constraints in RAW-domain demosaicing, color correction, and detail enhancement, this paper proposes RPBA-Net, an interpretable residual pyramid bilateral affine…
This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application. Prior neural networks, such as ResNet, tend…
Computational imaging enables compact infrared systems, but deep-learning pipelines that combine image reconstruction and object detection often introduce substantial inference latency. Most existing acceleration strategies compress the…
The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. However, this approach does not fully…
This paper proposes Deep Bi-Dense Networks (DBDN) for single image super-resolution. Our approach extends previous intra-block dense connection approaches by including novel inter-block dense connections. In this way, feature information…
Monocular depth estimation aims at estimating a pixelwise depth map for a single image, which has wide applications in scene understanding and autonomous driving. Existing supervised and unsupervised methods face great challenges.…
Portable backscatter imaging systems (PBI) integrate an X-ray source and detector in a single unit, utilizing Compton scattering photons to rapidly acquire superficial or shallow structural information of an inspected object through…