Disentangling Random and Cyclic Effects in Time-Lapse Sequences

• URL: http://arxiv.org/abs/2207.01413v1
• Date: Mon, 4 Jul 2022 13:49:04 GMT
• Title: Disentangling Random and Cyclic Effects in Time-Lapse Sequences
• Authors: Erik H\"ark\"onen, Miika Aittala, Tuomas Kynk\"a\"anniemi, Samuli Laine, Timo Aila, Jaakko Lehtinen
• Abstract summary: We introduce the problem of disentangling time-lapse sequences in a way that allows separate, after-the-fact control of overall trends, cyclic effects, and random effects in the images. Our approach is based on Generative Adversarial Networks (GAN) that are conditioned with the time coordinate of the time-lapse sequence. We show that our models are robust to defects in the training data, enabling us to amend some of the practical difficulties in capturing long time-lapse sequences.
• Score: 32.91054260622378
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time-lapse image sequences offer visually compelling insights into dynamic processes that are too slow to observe in real time. However, playing a long time-lapse sequence back as a video often results in distracting flicker due to random effects, such as weather, as well as cyclic effects, such as the day-night cycle. We introduce the problem of disentangling time-lapse sequences in a way that allows separate, after-the-fact control of overall trends, cyclic effects, and random effects in the images, and describe a technique based on data-driven generative models that achieves this goal. This enables us to "re-render" the sequences in ways that would not be possible with the input images alone. For example, we can stabilize a long sequence to focus on plant growth over many months, under selectable, consistent weather. Our approach is based on Generative Adversarial Networks (GAN) that are conditioned with the time coordinate of the time-lapse sequence. Our architecture and training procedure are designed so that the networks learn to model random variations, such as weather, using the GAN's latent space, and to disentangle overall trends and cyclic variations by feeding the conditioning time label to the model using Fourier features with specific frequencies. We show that our models are robust to defects in the training data, enabling us to amend some of the practical difficulties in capturing long time-lapse sequences, such as temporary occlusions, uneven frame spacing, and missing frames.

Related papers

• Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series [7.201938834736084]
  We propose a unified generative model for varying-length time series. We employ invertible transforms such as the delay embedding and the short-time Fourier transform. We show that our approach achieves consistently state-of-the-art results against strong baselines.
  arXiv  Detail & Related papers  (2024-10-25T13:06:18Z)
• Made to Order: Discovering monotonic temporal changes via self-supervised video ordering [89.0660110757949]
  We exploit a simple proxy task of ordering a shuffled image sequence, with time' serving as a supervisory signal. We introduce a transformer-based model for ordering of image sequences of arbitrary length with built-in attribution maps.
  arXiv  Detail & Related papers  (2024-04-25T17:59:56Z)
• TSLANet: Rethinking Transformers for Time Series Representation Learning [19.795353886621715]
  Time series data is characterized by its intrinsic long and short-range dependencies. We introduce a novel Time Series Lightweight Network (TSLANet) as a universal convolutional model for diverse time series tasks. Our experiments demonstrate that TSLANet outperforms state-of-the-art models in various tasks spanning classification, forecasting, and anomaly detection.
  arXiv  Detail & Related papers  (2024-04-12T13:41:29Z)
• SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams [44.02794438687478]
  Spike cameras have proven effective in capturing motion features and beneficial for solving this ill-posed problem. Existing methods fall into the supervised learning paradigm, which suffers from notable performance degradation when applied to real-world scenarios. We propose the first self-supervised framework for the task of spike-guided motion deblurring.
  arXiv  Detail & Related papers  (2024-03-14T15:29:09Z)
• Time Series as Images: Vision Transformer for Irregularly Sampled Time Series [32.99466250557855]
  This paper introduces a novel perspective by converting irregularly sampled time series into line graph images. We then utilize powerful pre-trained vision transformers for time series classification in the same way as image classification. Remarkably, despite its simplicity, our approach outperforms state-of-the-art specialized algorithms on several popular healthcare and human activity datasets.
  arXiv  Detail & Related papers  (2023-03-01T22:42:44Z)
• HyperTime: Implicit Neural Representation for Time Series [131.57172578210256]
  Implicit neural representations (INRs) have recently emerged as a powerful tool that provides an accurate and resolution-independent encoding of data. In this paper, we analyze the representation of time series using INRs, comparing different activation functions in terms of reconstruction accuracy and training convergence speed. We propose a hypernetwork architecture that leverages INRs to learn a compressed latent representation of an entire time series dataset.
  arXiv  Detail & Related papers  (2022-08-11T14:05:51Z)
• Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version [37.09531298150374]
  Traffic series forecasting is challenging due to complex time series patterns for the same time series patterns may vary across time, where, for example, there exist periods across a day showing stronger temporal correlations. Such-temporal models employ a shared parameter space irrespective of the time locations and the time periods and they assume that the temporal correlations are similar across locations and do not always hold across time which may not always be the case. We propose a framework that aims at turning ICD-temporal aware models to encode sub-temporal models.
  arXiv  Detail & Related papers  (2022-03-29T16:44:56Z)
• Efficient Video Segmentation Models with Per-frame Inference [117.97423110566963]
  We focus on improving the temporal consistency without introducing overhead in inference. We propose several techniques to learn from the video sequence, including a temporal consistency loss and online/offline knowledge distillation methods.
  arXiv  Detail & Related papers  (2022-02-24T23:51:36Z)
• Learning Temporal Dynamics from Cycles in Narrated Video [85.89096034281694]
  We propose a self-supervised solution to the problem of learning to model how the world changes as time elapses. Our model learns modality-agnostic functions to predict forward and backward in time, which must undo each other when composed. We apply the learned dynamics model without further training to various tasks, such as predicting future action and temporally ordering sets of images.
  arXiv  Detail & Related papers  (2021-01-07T02:41:32Z)
• Crowdsampling the Plenoptic Function [56.10020793913216]
  We present a new approach to novel view synthesis under time-varying illumination from such data. We introduce a new DeepMPI representation, motivated by observations on the sparsity structure of the plenoptic function. Our method can synthesize the same compelling parallax and view-dependent effects as previous MPI methods, while simultaneously interpolating along changes in reflectance and illumination with time.
  arXiv  Detail & Related papers  (2020-07-30T02:52:10Z)
• Efficient Semantic Video Segmentation with Per-frame Inference [117.97423110566963]
  In this work, we process efficient semantic video segmentation in a per-frame fashion during the inference process. We employ compact models for real-time execution. To narrow the performance gap between compact models and large models, new knowledge distillation methods are designed.
  arXiv  Detail & Related papers  (2020-02-26T12:24:32Z)

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.