Related papers: SparseMeXT Unlocking the Potential of Sparse Repre…

Neural Radiance Fields (NeRF) are an advanced technology that creates highly realistic images by learning about scenes through a neural network model. However, NeRF often encounters issues when there are not enough images to work with,…

We introduce the Sparsity Roofline, a visual performance model for evaluating sparsity in neural networks. The Sparsity Roofline jointly models network accuracy, sparsity, and theoretical inference speedup. Our approach does not require…

Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively…

Implicit neural representations are a promising new avenue of representing general signals by learning a continuous function that, parameterized as a neural network, maps the domain of a signal to its codomain; the mapping from spatial…

We propose a sparse and privacy-enhanced representation for Human Pose Estimation (HPE). Given a perspective camera, we use a proprietary motion vector sensor(MVS) to extract an edge image and a two-directional motion vector image at each…

To address the challenge of increasing network size, researchers have developed sparse models through network pruning. However, maintaining model accuracy while achieving significant speedups on general computing devices remains an open…

As urban environments manifest high levels of complexity it is of vital importance that safety systems embedded within autonomous vehicles (AVs) are able to accurately anticipate short-term future motion of nearby agents. This problem can…

Support estimation (SE) of a sparse signal refers to finding the location indices of the non-zero elements in a sparse representation. Most of the traditional approaches dealing with SE problem are iterative algorithms based on greedy…

In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach…

Sparse-view 3D reconstruction is essential for applications in which dense image acquisition is impractical, such as robotics, augmented/virtual reality (AR/VR), and autonomous systems. In these settings, minimal image overlap prevents…

High-Definition (HD) maps are essential for the safety of autonomous driving systems. While existing techniques employ camera images and onboard sensors to generate vectorized high-precision maps, they are constrained by their reliance on…

Neural Radiance Field (NeRF) has emerged as a leading technique for novel view synthesis, owing to its impressive photorealistic reconstruction and rendering capability. Nevertheless, achieving real-time NeRF rendering in large-scale scenes…

Joint Embedding Predictive Architectures (JEPA) have emerged as a powerful framework for learning general-purpose representations. However, these models often lack interpretability and suffer from inefficiencies due to dense embedding…

Sparse matrix vector multiplication (SpMV) is one of the most common operations in scientific and high-performance applications, and is often responsible for the application performance bottleneck. While the sparse matrix representation has…

Sparse representation has attracted much attention from researchers in fields of signal processing, image processing, computer vision and pattern recognition. Sparse representation also has a good reputation in both theoretical research and…

As a result of several successful applications in computer vision and image processing, sparse representation (SR) has attracted significant attention in multi-sensor image fusion. Unlike the traditional multiscale transforms (MSTs) that…

We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels. The model works simultaneously for both indoor/outdoor scenes and produces state-of-the-art dense depth…

This work introduces a new training and compression pipeline to build Nested Sparse ConvNets, a class of dynamic Convolutional Neural Networks (ConvNets) suited for inference tasks deployed on resource-constrained devices at the edge of the…

This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to methods that rely on variational autoencoders (VAEs) to generate discrete occupancy tokens, which inherently…

Recent work in Deep Learning has re-imagined the representation of data as functions mapping from a coordinate space to an underlying continuous signal. When such functions are approximated by neural networks this introduces a compelling…