相关论文: Efficient stereo matching on embedded GPUs with ze…

The study of approximate matching in the Massively Parallel Computations (MPC) model has recently seen a burst of breakthroughs. Despite this progress, however, we still have a far more limited understanding of maximal matching which is one…

The color video inpainting problem is one of the most challenging problem in the modern imaging science. It aims to recover a color video from a small part of pixels that may contain noise. However, there are less of robust models that can…

Convolutional neural network (CNN) inference on mobile devices demands efficient hardware acceleration of low-precision (INT8) general matrix multiplication (GEMM). Exploiting data sparsity is a common approach to further accelerate GEMM…

3D Gaussian Splatting (3DGS) renders pixels by rasterizing Gaussian primitives, where conditional alpha-blending dominates the computational cost in the rendering pipeline. This paper proposes TC-GS, an algorithm-independent universal…

Neural image compression methods have seen increasingly strong performance in recent years. However, they suffer orders of magnitude higher computational complexity compared to traditional codecs, which hinders their real-world deployment.…

An efficient hardware implementation for Simultaneous Localization and Mapping (SLAM) methods is of necessity for mobile autonomous robots with limited computational resources. In this paper, we propose a resource-efficient FPGA…

While zero-shot diffusion-based compression methods have seen significant progress in recent years, they remain notoriously slow and computationally demanding. This paper presents an efficient zero-shot diffusion-based compression method…

Composed Image Retrieval (CIR) aims to retrieve a target image based on a reference image and conditioning text, enabling controllable image searches. The mainstream Zero-Shot (ZS) CIR methods bypass the need for expensive training CIR…

Photonic tensor cores (PTCs) are essential building blocks for optical artificial intelligence (AI) accelerators based on programmable photonic integrated circuits. Most PTC designs today are manually constructed, with low design efficiency…

This work introduces a novel method for surface normal estimation from rectified stereo image pairs, leveraging affine transformations derived from disparity values to achieve fast and accurate results. We demonstrate how the rectification…

Crowd counting is a task of estimating the number of the crowd through images, which is extremely valuable in the fields of intelligent security, urban planning, public safety management, and so on. However, the existing counting methods…

3D Gaussian Splatting (3DGS) has emerged as a leading neural rendering technique for high-fidelity view synthesis, prompting the development of dedicated 3DGS accelerators for resource-constrained platforms. The conventional decoupled…

In this paper, we have proposed a novel method for stereo disparity estimation by combining the existing methods of block based and region based stereo matching. Our method can generate dense disparity maps from disparity measurements of…

Models for streaming speech translation (ST) can achieve high accuracy and low latency if they're developed with vast amounts of paired audio in the source language and written text in the target language. Yet, these text labels for the…

State-of-the-art supervised stereo matching methods have achieved remarkable performance on various benchmarks. However, their generalization to real-world scenarios remains challenging due to the scarcity of annotated real-world stereo…

The escalating challenges of managing vast sensor-generated data, particularly in audio applications, necessitate innovative solutions. Current systems face significant computational and storage demands, especially in real-time applications…

Stereo matching algorithms usually consist of four steps, including matching cost calculation, matching cost aggregation, disparity calculation, and disparity refinement. Existing CNN-based methods only adopt CNN to solve parts of the four…

Classification based on Zero-shot Learning (ZSL) is the ability of a model to classify inputs into novel classes on which the model has not previously seen any training examples. Providing an auxiliary descriptor in the form of a set of…

Recent advances in high-resolution CT-imaging technology are creating a new class of ultra-high resolved micro-structural datasets that challenge the limits of traditional homogenization approaches. While state-of-the-art FFT-based…

With the upcoming generation of telescopes, cluster scale strong gravitational lenses will act as an increasingly relevant probe of cosmology and dark matter. The better resolved data produced by current and future facilities requires…