Related papers: The CUDA LATCH Binary Descriptor: Because Sometime…

This paper performs a comprehensive and comparative evaluation of the state of the art local features for the task of image based 3D reconstruction. The evaluated local features cover the recently developed ones by using powerful machine…

Existing works often focus on reducing the architecture redundancy for accelerating image classification but ignore the spatial redundancy of the input image. This paper proposes an efficient image classification pipeline to solve this…

Online 3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage. Although causal variants of VGGT address this challenge through a key-value (KV) cache mechanism, the cache grows…

Lattice spin models are useful for studying critical phenomena and allow the extraction of equilibrium and dynamical properties. Simulations of such systems are usually based on Monte Carlo (MC) techniques, and the main difficulty is often…

Recently, lane detection has made great progress with the rapid development of deep neural networks and autonomous driving. However, there exist three mainly problems including characterizing lanes, modeling the structural relationship…

This paper describes an optimized single-stage deep convolutional neural network to detect objects in urban environments, using nothing more than point cloud data. This feature enables our method to work regardless the time of the day and…

Debugging CUDA programs has long been challenging because failures often arise from subtle interactions among hardware behavior, compiler decisions, memory hierarchy, and asynchronous execution. More importantly, with the rapid expansion of…

Binary descriptors have been instrumental in the recent evolution of computationally efficient sparse image alignment algorithms. Increasingly, however, the vision community is interested in dense image alignment methods, which are more…

We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction. The core of our method is a deep convolutional neural net that takes in RGB, depth, and normal information of a planar patch in an…

Two new algorithms are described for matching two dimensional coordinate lists of point sources that are signifcantly faster than previous methods. By matching rarely occurring triangles (or more complex shapes) in the two lists, and by…

Recent years have witnessed the increasing popularity of learning based methods to enhance the color and tone of photos. However, many existing photo enhancement methods either deliver unsatisfactory results or consume too much…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or fine-tune…

Recently, deep learning-based image enhancement algorithms achieved state-of-the-art (SOTA) performance on several publicly available datasets. However, most existing methods fail to meet practical requirements either for visual perception…

Block-tridiagonal systems are prevalent in state estimation and optimal control, and solving these systems is often the computational bottleneck. Improving the underlying solvers therefore has a direct impact on the real-time performance of…

Diffusion models learn strong image priors that can be leveraged to solve inverse problems like medical image reconstruction. However, for real-world applications such as 3D Computed Tomography (CT) imaging, directly training diffusion…

In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional…

We present an efficient, elastic 3D LiDAR reconstruction framework which can reconstruct up to maximum LiDAR ranges (60 m) at multiple frames per second, thus enabling robot exploration in large-scale environments. Our approach only…

We discuss the CUDA approach to the simulation of pure gauge Lattice SU(2). CUDA is a hardware and software architecture developed by NVIDIA for computing on the GPU. We present an analysis and performance comparison between the GPU and CPU…

The design of complexity-aware cascaded detectors, combining features of very different complexities, is considered. A new cascade design procedure is introduced, by formulating cascade learning as the Lagrangian optimization of a risk that…