Related papers: An Error-Surface-Based Fractional Motion Estimatio…
Vision algorithms can be executed directly on the image sensor when implemented on the next-generation sensors known as focal-plane sensor-processor arrays (FPSP)s, where every pixel has a processor. FPSPs greatly improve latency, reducing…
3D reconstruction from videos has become increasingly popular for various applications, including navigation for autonomous driving of robots and drones, augmented reality (AR), and 3D modeling. This task often combines traditional…
Conservation Voltage Reduction (CVR) relies on the effective coordination of slow-acting devices, such as OLTCs and CBs, and fast-acting devices, such as SVGs and PV inverters, typically implemented through a hierarchical multi-stage…
Feature compression, as an important branch of video coding for machines (VCM), has attracted significant attention and exploration. However, the existing methods mainly focus on intra-feature similarity, such as the Mean Squared Error…
Video Frame Interpolation (VFI) is a core low-level vision task that synthesizes intermediate frames between existing ones while ensuring spatial and temporal coherence. Over the past decades, VFI methodologies have evolved from classical…
Video Coding for Machines (VCM) aims to compress visual signals for machine analysis. However, existing methods only consider a few machines, neglecting the majority. Moreover, the machine's perceptual characteristics are not leveraged…
In this study, an image-assisted Approximate Bayesian Computation (ABC) parameter inverse method is proposed to identify the design parameters. In the proposed method, the images are mapped to a low-dimensional latent space by Variational…
Machine-learning force fields can deliver accurate molecular dynamics (MD) at high computational cost. For SO(3)-equivariant models such as MACE, there is little systematic evidence on whether reduced-precision arithmetic and GPU-optimized…
It has been shown, that high resolution images can be acquired using a low resolution sensor with non-regular sampling. Therefore, post-processing is necessary. In terms of video data, not only the spatial neighborhood can be used to assist…
The rate-distortion performance of neural image compression models has exceeded the state-of-the-art for non-learned codecs, but neural codecs are still far from widespread deployment and adoption. The largest obstacle is having efficient…
Reconstructing real-world 3D objects has numerous applications in computer vision, such as virtual reality, video games, and animations. Ideally, 3D reconstruction methods should generate high-fidelity results with 3D consistency in…
In this paper we develop the first fine-grained rounding error analysis of finite element (FE) cell kernels and assembly. The theory includes mixed-precision implementations and accounts for hardware-acceleration via matrix multiplication…
Neuromorphic hardware platforms can significantly lower the energy overhead of a machine learning inference task. We present a design-technology tradeoff analysis to implement such inference tasks on the processing elements (PEs) of a Non-…
Despite the continued successes of computationally efficient deep neural network architectures for video object detection, performance continually arrives at the great trilemma of speed versus accuracy versus computational resources (pick…
Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additional guidance, the large motion between frames makes this…
Foundation-model-based monocular depth estimation offers a viable alternative to active sensors for robot perception, yet its computational cost often prohibits deployment on edge platforms. Existing methods perform independent per-frame…
In High Efficiency Video Coding (HEVC), excellent rate-distortion (RD) performance is achieved in part by having a flexible quadtree coding unit (CU) partition and a large number of intra-prediction modes. Such an excellent RD performance…
The growing demand for edge computing and AI drives research into analog in-memory computing using memristors, which overcome data movement bottlenecks by computing directly within memory. However, device failures and variations critically…
We consider the problem of capturing distortions arising from changes in frame rate as part of Video Quality Assessment (VQA). Variable frame rate (VFR) videos have become much more common, and streamed videos commonly range from 30 frames…
With the skyrocketing costs of GPUs and their virtual instances in the cloud, there is a significant desire to use CPUs for large language model (LLM) inference. KV cache update, often implemented as allocation, copying, and in-place…