Filters








278 Hits in 4.2 sec

A Temporally-Aware Interpolation Network for Video Frame Inpainting [article]

Ximeng Sun, Ryan Szeto, Jason J. Corso
<span title="2018-11-03">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We devise a pipeline composed of two modules: a bidirectional video prediction module, and a temporally-aware frame interpolation module.  ...  We propose the first deep learning solution to video frame inpainting, a challenging instance of the general video inpainting problem with applications in video editing, manipulation, and forensics.  ...  Temporally-Aware Interpolation Network φ blend Following the Bidirectional Video Prediction Network, the Temporally-Aware Interpolation Network φ blend takes corresponding pairs of frames from M P V and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.07218v2">arXiv:1803.07218v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kvduxohhpfau7fl2s5wkqgkbwq">fatcat:kvduxohhpfau7fl2s5wkqgkbwq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930023823/https://arxiv.org/pdf/1803.07218v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d5/6c/d56c5f0a23ecef2eeaad1b882829d709fa172632.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.07218v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

3D Moments from Near-Duplicate Photos [article]

Qianqian Wang, Zhengqi Li, David Salesin, Noah Snavely, Brian Curless, Janne Kontkanen
<span title="2022-05-12">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
As output, we produce a video that smoothly interpolates the scene motion from the first photo to the second, while also producing camera motion with parallax that gives a heightened sense of 3D.  ...  This representation enables motion interpolation along with independent control of the camera viewpoint.  ...  We thank Richard Tucker, Tianfan Xue, Andrew Liu, Jamie Aspinall, Fitsum Reda and Forrester Cole for help, discussion and support.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.06255v1">arXiv:2205.06255v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ckszn3gvfreaxpstyb443taboi">fatcat:ckszn3gvfreaxpstyb443taboi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220514220329/https://arxiv.org/pdf/2205.06255v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/39/12/3912c18f219cb2459907684ad9e3e6f25966374a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.06255v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN [article]

Ya-Liang Chang, Zhe Yu Liu, Kuan-Ying Lee, Winston Hsu
<span title="2019-07-23">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Free-form video inpainting is a very challenging task that could be widely used for video editing such as text removal.  ...  In addition, we collect videos and design a free-form mask generation algorithm to build the free-form video inpainting (FVI) dataset for training and evaluation of video inpainting models.  ...  For frame interpolation, masks could be added between frames.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.10247v3">arXiv:1904.10247v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/65qapaft2fdfrdy3nst2kdufvq">fatcat:65qapaft2fdfrdy3nst2kdufvq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191017093612/https://arxiv.org/pdf/1904.10247v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e6/d2/e6d22659c8b9c1a0de6089400adeff84693fa37f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.10247v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An Internal Learning Approach to Video Inpainting [article]

Haotian Zhang, Long Mai, Ning Xu, Zhaowen Wang, John Collomosse, Hailin Jin
<span title="2019-09-17">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We take a generative approach to inpainting based on internal (within-video) learning without reliance upon an external corpus of visual data to train a one-size-fits-all model for the large space of general  ...  In extending DIP to video we make two important contributions. First, we show that coherent video inpainting is possible without a priori training.  ...  We thank Flickr users Horia Varlan, tyalis 2, Andy Tran and Ralf Kayser for their permissions to use their videos in our experiments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.07957v1">arXiv:1909.07957v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gzann7srsfcvtpzqpks57zadba">fatcat:gzann7srsfcvtpzqpks57zadba</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930202730/https://arxiv.org/pdf/1909.07957v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cc/bb/ccbb652bca1b5f795333c7dc148ad2f01caf9e35.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.07957v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Dynamic Object Removal and Spatio-Temporal RGB-D Inpainting via Geometry-Aware Adversarial Learning [article]

Borna Bešić, Abhinav Valada
<span title="2022-01-03">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
coherent manner, without relying on future frame information.  ...  We propose the novel geometry-aware DynaFill architecture that follows a coarse-to-fine topology and incorporates our gated recurrent feedback mechanism to adaptively fuse information from previous timesteps  ...  [27] propose an approach to predict both image frames and optical flow maps for video inpainting by optimizing the network directly on the input video.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.05058v4">arXiv:2008.05058v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vi37iulxizaxpmudq7zpo7hv5a">fatcat:vi37iulxizaxpmudq7zpo7hv5a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210302050718/https://arxiv.org/pdf/2008.05058v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f5/43/f54323319fcfd700b0bf2bef51473ed6c3a64c03.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.05058v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Guest Editorial: Image and Video Inpainting and Denoising

Sergio Escalera, Hugo Jair Escalante, Xavier Baro, Isabelle Guyon, Meysam Madadi, Jun Wan, Stephane Ayache, Yagmur Gucluturk, Umut Guclu
<span title="2020-05-01">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
Youtube-VOS [8], DAVIS [9] [10] Video frame inpainting Bidirectional (convolutional LSTM-based encoder-decoder) prediction model and a temporally aware frame interpolation model KTH Actions [11]  ...  temporal model for frame aggregation based on a encoder-decoder architecture ChaLearn video De-Captioning [7].  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2020.2971291">doi:10.1109/tpami.2020.2971291</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2ejjleudx5dwlj54fws2t6gqhe">fatcat:2ejjleudx5dwlj54fws2t6gqhe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201107185418/https://ieeexplore.ieee.org/ielx7/34/9055268/09055328.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7c/1b/7c1b465db8fb1f4ef89302ffbf92f83914e610d9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2020.2971291"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Revealing Disocclusions in Temporal View Synthesis through Infilling Vector Prediction [article]

Vijayalakshmi Kanchana, Nagabhushan Somraj, Suraj Yadwad, Rajiv Soundararajan
<span title="2021-10-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We consider the problem of temporal view synthesis, where the goal is to predict a future video frame from the past frames using knowledge of the depth and relative camera motion.  ...  We design a learning framework to predict the infilling vector by computing a temporal prior that reflects past infilling directions and a normalized depth map as input to the network.  ...  Acknowledgments This work was supported by a grant from Qualcomm. We also thank Vinay Melkote and Ajit Rao for helpful discussions and comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.08805v1">arXiv:2110.08805v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/upx2vq66sbhhtnzcz5bcjwjcjq">fatcat:upx2vq66sbhhtnzcz5bcjwjcjq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211020215618/https://arxiv.org/pdf/2110.08805v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4e/fe/4efecce97c9da050095bfdd6be0f882691b98763.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.08805v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Semantic-Aware Dynamics for Video Prediction [article]

Xinzhu Bei, Yanchao Yang, Stefano Soatto
<span title="2021-04-20">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The appearance of the scene is warped from past frames using the predicted motion in co-visible regions; dis-occluded regions are synthesized with content-aware inpainting utilizing the predicted scene  ...  We propose an architecture and training scheme to predict video frames by explicitly modeling dis-occlusions and capturing the evolution of semantically consistent regions in the video.  ...  The inpainting network is a modified U-Net [33] , conditioned on predicted anchor frames and semantic maps.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.09762v1">arXiv:2104.09762v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rzbewbus4zftpn6cu4e6asfoi4">fatcat:rzbewbus4zftpn6cu4e6asfoi4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210422041731/https://arxiv.org/pdf/2104.09762v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/83/7d/837d57006a94a308bbceff0481917fdd41094be9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.09762v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Comprehensive Study on Novel Video Frame Interpolation Methods

Hrishikesh Mahajan, Yash Shekhadar, Shebin Silvister, Dheeraj Komandur, Nitin Pise
<span title="2021-07-19">2021</span> <i title="Foundation of Computer Science"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b637noqf3vhmhjevdfk3h5pdsu" style="color: black;">International Journal of Computer Applications</a> </i> &nbsp;
Video Frame Interpolation is the process of generating frames between two or more frames of a video.  ...  Today, methods such as Optical Flow, Depth mapping and Visibility Mapping techniques are used to interpolate frames of high quality with less emphasis on Learning-Based methods.  ...  The interpolated frame is generated using a context aware video frame synthesis neural network. The model uses a GridNet architecture which is well suited for pixel-wise problems.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/ijca2021921472">doi:10.5120/ijca2021921472</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dixmtwjhk5hrpim7zvg3jq7w64">fatcat:dixmtwjhk5hrpim7zvg3jq7w64</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210721085936/https://www.ijcaonline.org/archives/volume183/number15/mahajan-2021-ijca-921472.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/82/93/8293100d8d69f47e6ab3ae3af9d540301371faad.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/ijca2021921472"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Intuitive Facial Animation Editing Based On A Generative RNN Framework [article]

Eloïse Berson, Catherine Soladié, Nicolas Stoiber
<span title="2020-10-12">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Inspired by recent image inpainting methods, we design a generative recurrent neural network that generates realistic motion into designated segments of an existing facial animation, optionally following  ...  For the last decades, the concern of producing convincing facial animation has garnered great interest, that has only been accelerating with the recent explosion of 3D content in both entertainment and  ...  For instance, on a video outside the dataset, we observe that the face capture yields imprecise animation frames of the mouth.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05655v1">arXiv:2010.05655v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z6udw7utqncidojlr7562htyiq">fatcat:z6udw7utqncidojlr7562htyiq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201120221421/https://arxiv.org/pdf/2010.05655v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/71/1a/711a95275b97b3524be65431bd7d87d98ec326b3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.05655v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Disentangling Propagation and Generation for Video Prediction [article]

Hang Gao, Huazhe Xu, Qi-Zhi Cai, Ruth Wang, Fisher Yu, Trevor Darrell
<span title="2019-08-05">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Moreover, in contrast to prior works where confidence is jointly learned with flow and appearance using a single network, we compute confidence after a warping step, and employ a separate network to inpaint  ...  We introduce a confidence-aware warping operator which gates the output of pixel predictions from a flow predictor for non-occluded regions and from a context encoder for occluded regions.  ...  a warping step, and employ a separate network to inpaint flow (b) to its near future target (c).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.00452v2">arXiv:1812.00452v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ukz6uht6pbb4tb3qxc5yshpah4">fatcat:ukz6uht6pbb4tb3qxc5yshpah4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827123327/https://arxiv.org/pdf/1812.00452v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ce/71/ce71c5b4c959c34715503a5980e457e700db9e70.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.00452v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Depth-Aware Motion Magnification [chapter]

Julian F. P. Kooij, Jan C. van Gemert
<span title="">2016</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Current approaches require a manual drawn pixel mask over all frames in the area of interest which is cumbersome and errorprone.  ...  We show results for a medical application (tremors) where we improve current baselines for motion magnification and motion measurements.  ...  Inpainting can be done efficiently [20] , making it in principle suitable for video processing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-46484-8_28">doi:10.1007/978-3-319-46484-8_28</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nh6xqkee3rg2jld5kcy2o5gvr4">fatcat:nh6xqkee3rg2jld5kcy2o5gvr4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190223205812/http://pdfs.semanticscholar.org/4d3e/166acd82bd1fb12a8d8d671b4c1f941352d5.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4d/3e/4d3e166acd82bd1fb12a8d8d671b4c1f941352d5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-46484-8_28"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Video Generation from Text Employing Latent Path Construction for Temporal Modeling [article]

Amir Mazaheri, Mubarak Shah
<span title="2021-07-29">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We tackle the complicated problem of video generation by regressing the latent representations of the first and last frames and employing a context-aware interpolation method to build the latent representations  ...  In this paper, we tackle the text to video generation problem, which is a conditional form of video generation.  ...  In this paper, we propose a novel method to capture temporal dynamics by first regressing the first and last frames' latent representations from text description and employing a context-aware interpolation  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.13766v1">arXiv:2107.13766v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s3dmfv7p5fdu5i7y64ajrpirtu">fatcat:s3dmfv7p5fdu5i7y64ajrpirtu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210805031726/https://arxiv.org/pdf/2107.13766v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b0/a0/b0a0057b70382123e994c1ac1e970571f81b35bb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.13766v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

3D Ken Burns Effect from a Single Image [article]

Simon Niklaus, Long Mai, Jimei Yang, Feng Liu
<span title="2019-09-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To address the limitations of existing depth estimation methods such as geometric distortions, semantic distortions, and inaccurate depth boundaries, we develop a semantic-aware neural network for depth  ...  To address disocclusions while maintaining geometrically and temporally coherent synthesis results, we utilize context-aware color- and depth-inpainting to fill in the missing information in the extreme  ...  We would like to thank Tobias Koch for his help with the iBims-1 benchmark. We are grateful for being allowed to use footage from Ian D. Keating (Figure 1, top  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.05483v1">arXiv:1909.05483v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/smmzhme73nbkhlqff5hudhkcai">fatcat:smmzhme73nbkhlqff5hudhkcai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928201523/https://arxiv.org/pdf/1909.05483v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c6/ff/c6ff787a0190e5275e193c9bf57f672c48011d33.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.05483v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Self-Supervision by Prediction for Object Discovery in Videos [article]

Beril Besbinar, Pascal Frossard
<span title="2021-03-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Initial experiments confirm that the proposed pipeline is a promising step towards object-centric video prediction.  ...  the predicted frame.  ...  encodings help neural networks to learn position-aware representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.05669v1">arXiv:2103.05669v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/trixe3eoqza5tilaku5q447q6e">fatcat:trixe3eoqza5tilaku5q447q6e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210312001259/https://arxiv.org/pdf/2103.05669v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/12/2d/122df510c779e0f3efa29794dfe689673243fd7b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.05669v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 278 results