paper-with-me

홈 › Papers

Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing

2026-03-23 · Weitong Cai, Hang Zhang, Yukai Huang, Shitong Sun, Jiankang Deng, Songcen Xu, Jifei Song, Zhensong Zhang arxiv

Always-on sensing is essential for next-generation edge/wearable AI systems, yet continuous high-fidelity RGB video capture remains prohibitively expensive for resource-constrained mobile and edge platforms. We present a new paradigm for efficient streaming video understanding: grayscale-always, color-on-demand. Through preliminary studies, we discover that color is not always necessary. Sparse RGB frames suffice for comparable performance when temporal structure is preserved via continuous grayscale streams. Building on this insight, we propose ColorTrigger, an online training-free trigger that selectively activates color capture based on windowed grayscale affinity analysis. Designed for real-time edge deployment, ColorTrigger uses lightweight quadratic programming to detect chromatic redundancy causally, coupled with credit-budgeted control and dynamic token routing to jointly reduce sensing and inference costs. On streaming video understanding benchmarks, ColorTrigger achieves 91.6% of full-color baseline performance while using only 8.1% RGB frames, demonstrating substantial color redundancy in natural videos and enabling practical always-on video sensing on resource-constrained devices.

📄 PDF Abstract BibTeX arXiv:2603.22466

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

What's color got to do with it? Face recognition in grayscale

2023-09-11 · Aman Bhatta, Domingo Mery, Haiyu Wu, Joyce Annan 외

State-of-the-art deep CNN face matchers are typically created using extensive training sets of color face images. Our study reveals that such matchers attain virtually identical accuracy when trained on either grayscale …

Face Recognition

Nighttime Defogging Using High-Low Frequency Decomposition and Grayscale-Color Networks

2020-08-01 · ECCV 2020 8 · Wending Yan, Robby T. Tan, Dengxin Dai

In this paper, we address the problem of nighttime defogging from a single image. We propose a framework consisting of two main modules: grayscale and color modules. Given an RGB foggy nighttime image, our grayscale modu…

Vocal Bursts Intensity Prediction

ISPDiffuser: Learning RAW-to-sRGB Mappings with Texture-Aware Diffusion Models and Histogram-Guided Color Consistency

2025-03-25 · Yang Ren, Hai Jiang, Menglong Yang, Wei Li 외

RAW-to-sRGB mapping, or the simulation of the traditional camera image signal processor (ISP), aims to generate DSLR-quality sRGB images from raw data captured by smartphone sensors. Despite achieving comparable results …

Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization

2025-05-21 · Satoshi Kosugi

Exemplar-based image colorization aims to colorize a grayscale image using a reference color image, ensuring that reference colors are applied to corresponding input regions based on their semantic similarity. To achieve…

ColorizationImage ColorizationSemantic SimilaritySemantic Textual Similarity

SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network

2020-11-23 · Yuzhi Zhao, Lai-Man Po, Kwok-Wai Cheung, Wing-Yin Yu 외

Given a grayscale photograph, the colorization system estimates a visually plausible colorful image. Conventional methods often use semantics to colorize grayscale images. However, in these methods, only classification s…

ColorizationDecoderGenerative Adversarial Network