Lossy Event Compression based on Image-derived Quad Trees and Poisson Disk Sampling

• URL: http://arxiv.org/abs/2005.00974v2
• Date: Tue, 1 Dec 2020 07:41:48 GMT
• Title: Lossy Event Compression based on Image-derived Quad Trees and Poisson Disk Sampling
• Abstract summary: We propose a novel event compression algorithm based on a quad tree (QT) segmentation map derived from the adjacent intensity images. Our algorithm achieves greater than 6x compression compared to the state of the art.
• Score: 6.5364852148089545
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With several advantages over conventional RGB cameras, event cameras have provided new opportunities for tackling visual tasks under challenging scenarios with fast motion, high dynamic range, and/or power constraint. Yet unlike image/video compression, the performance of event compression algorithm is far from satisfying and practical. The main challenge for compressing events is the unique event data form, i.e., a stream of asynchronously fired event tuples each encoding the 2D spatial location, timestamp, and polarity (denoting an increase or decrease in brightness). Since events only encode temporal variations, they lack spatial structure which is crucial for compression. To address this problem, we propose a novel event compression algorithm based on a quad tree (QT) segmentation map derived from the adjacent intensity images. The QT informs 2D spatial priority within the 3D space-time volume. In the event encoding step, events are first aggregated over time to form polarity-based event histograms. The histograms are then variably sampled via Poisson Disk Sampling prioritized by the QT based segmentation map. Next, differential encoding and run length encoding are employed for encoding the spatial and polarity information of the sampled events, respectively, followed by Huffman encoding to produce the final encoded events. Our Poisson Disk Sampling based Lossy Event Compression (PDS-LEC) algorithm performs rate-distortion based optimal allocation. On average, our algorithm achieves greater than 6x compression compared to the state of the art.

Related papers

• Lossy Event Compression: From Event Stream Distortion to Task Performance [4.026541089436386]
  Lossy compression is essential for practical deployment of event cameras.<n>Existing event stream distortion metrics fail to reliably predict compression-induced degradation at the task level.<n>This paper introduces two fundamentally different event compression pipelines.
  arXiv  Detail & Related papers  (2026-08-28T15:12:56Z)
• ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization [59.481950697968706]
  We propose Progressive Generative Image Compression (ProGIC), a compact built on residual vector quantization (RVQ)<n>In RVQ, a sequence of vector quantizers encodes the residuals stage by stage, each with its own codebook.<n>We pair this with a lightweight backbone based on depthwise-separable convolutions and small attention blocks, enabling practical deployment on both GPU and CPU-only devices.
  arXiv  Detail & Related papers  (2026-03-03T11:47:05Z)
• Geometric-Photometric Event-based 3D Gaussian Ray Tracing [36.13207105469902]
  Event cameras offer a high temporal resolution over traditional frame-based cameras.<n>It has been unclear how event-based 3D Gaussian Splatting approaches could leverage fine-grained temporal information of sparse events.<n>This work proposes a framework to address the trade-off between accuracy and temporal resolution in event-based 3DGS.
  arXiv  Detail & Related papers  (2025-12-21T08:31:02Z)
• EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video Large Language Models [56.16721798968254]
  We propose an event-guided, training-free framework for efficient understanding, named EventSTU.<n>In the temporal domain, we design a coarse-to-fine sampling algorithm that the change-triggered property of event cameras to eliminate redundant large frames.<n>In the spatial domain, we achieves an adaptive token pruning algorithm that leverages the saliency of events as a zero-cost prior to guide spatial reduction.
  arXiv  Detail & Related papers  (2025-11-24T09:30:02Z)
• Deep Lossless Image Compression via Masked Sampling and Coarse-to-Fine Auto-Regression [8.6984128323386]
  We propose a deep lossless image compression via masked sampling and coarse-to-fine auto-regression.<n>It combines lossy reconstruction and progressive residual compression, which fuses contexts from various directions.<n>Our method achieves comparable compression performance on extensive datasets with competitive coding speed and more flexibility.
  arXiv  Detail & Related papers  (2025-03-14T09:29:55Z)
• Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need [53.584140947828004]
  Language large model (LLM) with unprecedented intelligence is a general-purpose lossless compressor for various data modalities. We propose P$2$-LLM, a next-pixel prediction-based LLM, which integrates various elaborated insights and methodologies. Experiments on benchmark datasets demonstrate that P$2$-LLM can beat SOTA classical and learned codecs.
  arXiv  Detail & Related papers  (2024-11-19T12:15:40Z)
• bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction [57.199618102578576]
  We propose bit2bit, a new method for reconstructing high-quality image stacks at original resolution from sparse binary quantatemporal image data. Inspired by recent work on Poisson denoising, we developed an algorithm that creates a dense image sequence from sparse binary photon data. We present a novel dataset containing a wide range of real SPAD high-speed videos under various challenging imaging conditions.
  arXiv  Detail & Related papers  (2024-10-30T17:30:35Z)
• Path-adaptive Spatio-Temporal State Space Model for Event-based Recognition with Arbitrary Duration [9.547947845734992]
  Event cameras are bio-inspired sensors that capture the intensity changes asynchronously and output event streams. We present a novel framework, dubbed PAST-Act, exhibiting superior capacity in recognizing events with arbitrary duration. We also build a minute-level event-based recognition dataset, named ArDVS100, with arbitrary duration for the benefit of the community.
  arXiv  Detail & Related papers  (2024-09-25T14:08:37Z)
• Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth [83.15263499262824]
  We prove that gradient descent converges to a solution that completely disregards the sparse structure of the input. We show how to improve upon Gaussian performance for the compression of sparse data by adding a denoising function to a shallow architecture. We validate our findings on image datasets, such as CIFAR-10 and MNIST.
  arXiv  Detail & Related papers  (2024-02-07T16:32:29Z)
• Neural-based Compression Scheme for Solar Image Data [8.374518151411612]
  We propose a neural network-based lossy compression method to be used in NASA's data-intensive imagery missions. In this work, we propose an adversarially trained neural network, equipped with local and non-local attention modules to capture both the local and global structure of the image. As a proof of concept for use of this algorithm in SDO data analysis, we have performed coronal hole (CH) detection using our compressed images.
  arXiv  Detail & Related papers  (2023-11-06T04:13:58Z)
• Graph-based Asynchronous Event Processing for Rapid Object Recognition [59.112755601918074]
  Event cameras capture asynchronous events stream in which each event encodes pixel location, trigger time, and the polarity of the brightness changes. We introduce a novel graph-based framework for event cameras, namely SlideGCN. Our approach can efficiently process data event-by-event, unlock the low latency nature of events data while still maintaining the graph's structure internally.
  arXiv  Detail & Related papers  (2023-08-28T08:59:57Z)
• EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging [6.8372546605486555]
  We show that an UHD color video with high compression ratio can be reconstructed from a snapshot 2D measurement using a single end-to-end deep learning model with PSNR above 32 dB. Our method significantly outperforms all previous SOTA algorithms with better real-time performance.
  arXiv  Detail & Related papers  (2023-05-17T07:28:46Z)
• A Novel Approach for Neuromorphic Vision Data Compression based on Deep Belief Network [0.2578242050187029]
  A neuromorphic camera is an image sensor that emulates the human eyes capturing only changes in local brightness levels. This paper proposes a novel deep learning-based compression scheme for event data.
  arXiv  Detail & Related papers  (2022-10-27T12:21:14Z)
• Exploring Long- and Short-Range Temporal Information for Learned Video Compression [54.91301930491466]
  We focus on exploiting the unique characteristics of video content and exploring temporal information to enhance compression performance. For long-range temporal information exploitation, we propose temporal prior that can update continuously within the group of pictures (GOP) during inference. In that case temporal prior contains valuable temporal information of all decoded images within the current GOP. In detail, we design a hierarchical structure to achieve multi-scale compensation.
  arXiv  Detail & Related papers  (2022-08-07T15:57:18Z)
• Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis [40.249030338644225]
  Video-to-Video synthesis (Vid2Vid) has achieved remarkable results in generating a photo-realistic video from a sequence of semantic maps. Fast-Vid2Vid achieves around real-time performance as 20 FPS and saves around 8x computational cost on a single V100 GPU.
  arXiv  Detail & Related papers  (2022-07-11T17:57:57Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)

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.