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

• URL: http://arxiv.org/abs/2603.22466v1
• Date: Mon, 23 Mar 2026 18:32:36 GMT
• Title: Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing
• Abstract summary: We present a new paradigm for efficient streaming video understanding: grayscale-always, color-on-demand.<n>We propose ColorTrigger, an online training-free trigger that activates color capture based on windowed grayscale affinity analysis.<n>On streaming video understanding benchmarks, ColorTrigger achieves 91.6% of full-color baseline performance while using only 8.1% RGB frames.
• Score: 58.25947399492333
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• ENCORE: Event-Assisted Complementary Motion Refinement for Learned Video Compression [16.49973800168176]
  Event-Assisted Complementary Motion Refinement framework for learned video compression.<n> ENCORE achieves up to 20.80% PSNR-RGB and 22.14% MS-SSIM-RGB BD-rate savings.<n> experiments on BS-ERGB, HQ-EVFI, and CED demonstrate consistent gains across datasets and GOP lengths.
  arXiv  Detail & Related papers  (2026-07-30T11:10:13Z)
• RainDancer: RGB-Event Video Deraining with Rain-Oriented Spiking Dynamics [93.19893734404417]
  Video deraining aims to recover clean visual content from rainy videos for reliable perception under adverse weather.<n>Existing methods mainly rely on RGB sequences and temporal redundancy, but RGB-only restoration remains ambiguous in dynamic rainy scenes.<n>We propose RainDancer, a progressive RGB-Event video deraining framework based on a decompose-before-interact paradigm.
  arXiv  Detail & Related papers  (2026-07-15T13:08:21Z)
• One Channel to Rule Them All: Rethinking Input Representation for Visual Place Recognition [14.020214078011515]
  Visual Place Recognition is fundamental to long-term robot localization and SLAM.<n>Current systems overwhelmingly rely on RGB input, implicitly assuming color is necessary for global place recognition.<n>We find that grayscale matches RGB performance generally and outperforms it under severe appearance shifts.
  arXiv  Detail & Related papers  (2026-05-31T00:30:05Z)
• Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor [12.418360718687026]
  Motion blur arises when rapid scene changes occur during the exposure period, collapsing rich intra-exposure motion into a single RGB frame.<n>We propose Spatio-Temporal Difference Guided Deblur Net (STGDNet) to restore structure and color details lost in blurry RGB inputs.<n>Our method outperforms current RGB or event-based approaches in both synthetic CVS dataset and real-world evaluations.
  arXiv  Detail & Related papers  (2026-04-12T09:54:14Z)
• SwiTrack: Tri-State Switch for Cross-Modal Object Tracking [74.15663758681849]
  Cross-modal object tracking (CMOT) is an emerging task that maintains target consistency while the video stream switches between different modalities.<n>We propose SwiTrack, a novel state-switching framework that redefines CMOT through the deployment of three specialized streams.
  arXiv  Detail & Related papers  (2025-11-20T10:52:54Z)
• Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Tracking [74.15663758681849]
  We present Learning Frequency and Memory-Aware Prompts, a dual-adapter framework that injects lightweight prompts into a frozen RGB tracker.<n>A frequency-guided visual adapter adaptively transfers complementary cues across modalities.<n>A multilevel memory adapter with short, long, and permanent memory stores, updates, and retrieves reliable temporal context.
  arXiv  Detail & Related papers  (2025-06-30T15:38:26Z)
• VanGogh: A Unified Multimodal Diffusion-based Framework for Video Colorization [53.35016574938809]
  Video colorization aims to transform grayscale videos into vivid color representations while maintaining temporal consistency and structural integrity.<n>Existing video colorization methods often suffer from color bleeding and lack comprehensive control.<n>We introduce VanGogh, a unified multimodal diffusion-based framework for video colorization.
  arXiv  Detail & Related papers  (2025-01-16T12:20:40Z)
• LatentColorization: Latent Diffusion-Based Speaker Video Colorization [1.2641141743223379]
  We introduce a novel solution for achieving temporal consistency in video colorization. We demonstrate strong improvements on established image quality metrics compared to other existing methods. Our dataset encompasses a combination of conventional datasets and videos from television/movies.
  arXiv  Detail & Related papers  (2024-05-09T12:06:06Z)
• Event-based Continuous Color Video Decompression from Single Frames [36.4263932473053]
  We present ContinuityCam, a novel approach to generate a continuous video from a single static RGB image and an event camera stream.<n>Our approach combines continuous long-range motion modeling with a neural synthesis model, enabling frame prediction at arbitrary times within the events.
  arXiv  Detail & Related papers  (2023-11-30T18:59:23Z)
• Improving Video Colorization by Test-Time Tuning [79.67548221384202]
  We propose an effective method, which aims to enhance video colorization through test-time tuning. By exploiting the reference to construct additional training samples during testing, our approach achieves a performance boost of 13 dB in PSNR on average.
  arXiv  Detail & Related papers  (2023-06-25T05:36:40Z)
• GTM: Gray Temporal Model for Video Recognition [2.534039616389072]
  We propose a new input modality: gray stream, which can skip the conversion process from video to RGB, but also improve Channel-temporal modeling ability. We also propose a 1D Identity-wise Spatio-temporal Convolution (1D-ICSC) which captures the temporal relationship at channel-feature level within a computation budget.
  arXiv  Detail & Related papers  (2021-10-20T02:45:48Z)
• Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning [90.38674162878496]
  We propose a novel temporally consistent video colorization framework (TCVC) TCVC effectively propagates frame-level deep features in a bidirectional way to enhance the temporal consistency of colorization. Experiments demonstrate that our method can not only obtain visually pleasing colorized video, but also achieve clearly better temporal consistency than state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-10-09T13:00:14Z)
• VCGAN: Video Colorization with Hybrid Generative Adversarial Network [22.45196398040388]
  Hybrid Video Colorization with Hybrid Generative Adversarative Network (VCGAN) is an improved approach to colorization using end-to-end learning. Experimental results demonstrate that VCGAN produces higher-quality and temporally more consistent colorful videos than existing approaches.
  arXiv  Detail & Related papers  (2021-04-26T05:50:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.