{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/video-generation/papers/14","list_of":"/task/video-generation","task":"Video Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":14,"pages_in_order":15,"rows_per_page":100,"rows":[1301,1400],"of":1466,"counts":{"archive_papers_tagged":1466,"with_a_code_link":609,"where_syntology_ran_a_sample":257,"not_listed_spam_title":0,"listed":1466,"listed_where_code_ran":257,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":221,"every_run_a_failure_of_syntologys_instrument":36,"listed_with_a_run_with_no_instrument_failure":221,"listed_every_run_a_failure_of_syntologys_instrument":36,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/video-generation","prev":"/task/video-generation/papers/13","next":"/task/video-generation/papers/15","papers":[{"url":null,"slug":"art-boldsymbol-cdot-v-auto-regressive-text-to","title":"ART$\\boldsymbol{\\cdot}$V: Auto-Regressive Text-to-Video Generation with Diffusion Models","date":"2023-11-30","arxiv_id":"2311.18834","repositories_listed":0,"syntology":null},{"url":null,"slug":"microcinema-a-divide-and-conquer-approach-for","title":"MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation","date":"2023-11-30","arxiv_id":"2311.18829","repositories_listed":0,"syntology":null},{"url":null,"slug":"vidiff-translating-videos-via-multi-modal","title":"VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models","date":"2023-11-30","arxiv_id":"2311.18837","repositories_listed":0,"syntology":null},{"url":null,"slug":"motionzero-exploiting-motion-priors-for-zero","title":"MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation","date":"2023-11-28","arxiv_id":"2311.16635","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowzero-zero-shot-text-to-video-synthesis","title":"FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax","date":"2023-11-27","arxiv_id":"2311.15813","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt4video-a-unified-multimodal-large-language","title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","date":"2023-11-25","arxiv_id":"2311.16511","repositories_listed":0,"syntology":null},{"url":null,"slug":"adadiff-adaptive-step-selection-for-fast","title":"AdaDiff: Adaptive Step Selection for Fast Diffusion Models","date":"2023-11-24","arxiv_id":"2311.14768","repositories_listed":0,"syntology":null},{"url":null,"slug":"decouple-content-and-motion-for-conditional","title":"Decouple Content and Motion for Conditional Image-to-Video Generation","date":"2023-11-24","arxiv_id":"2311.14294","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt4motion-scripting-physical-motions-in-text","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","date":"2023-11-21","arxiv_id":"2311.12631","repositories_listed":0,"syntology":null},{"url":null,"slug":"movideo-motion-aware-video-generation-with","title":"MoVideo: Motion-Aware Video Generation with Diffusion Models","date":"2023-11-19","arxiv_id":"2311.11325","repositories_listed":0,"syntology":null},{"url":"/paper/make-pixels-dance-high-dynamic-video","slug":"make-pixels-dance-high-dynamic-video","title":"Make Pixels Dance: High-Dynamic Video Generation","date":"2023-11-18","arxiv_id":"2311.10982","repositories_listed":0,"syntology":null},{"url":null,"slug":"emu-video-factorizing-text-to-video","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","date":"2023-11-17","arxiv_id":"2311.10709","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-as-an-art-director-ladi-using-llms-to","title":"LLM as an Art Director (LaDi): Using LLMs to improve Text-to-Media Generators","date":"2023-11-07","arxiv_id":"2311.03716","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-hyperparameter-space-of-image","title":"Exploring the Hyperparameter Space of Image Diffusion Models for Echocardiogram Generation","date":"2023-11-02","arxiv_id":"2311.01567","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-noise-pursuit-for-augmenting-text-to","title":"POS: A Prompts Optimization Suite for Augmenting Text-to-Video Generation","date":"2023-11-02","arxiv_id":"2311.00949","repositories_listed":0,"syntology":null},{"url":null,"slug":"videodreamer-customized-multi-subject-text-to","title":"VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning","date":"2023-11-02","arxiv_id":"2311.00990","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-u-making-diffusion-models-faster","title":"The Missing U for Efficient Diffusion Models","date":"2023-10-31","arxiv_id":"2310.20092","repositories_listed":0,"syntology":null},{"url":null,"slug":"echocardiography-video-synthesis-from-end","title":"Echocardiography video synthesis from end diastolic semantic map via diffusion model","date":"2023-10-11","arxiv_id":"2310.07131","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-grounded-video-diffusion-models","title":"LLM-grounded Video Diffusion Models","date":"2023-09-29","arxiv_id":"2309.17444","repositories_listed":0,"syntology":null},{"url":null,"slug":"osm-net-one-to-many-one-shot-talking-head","title":"OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions","date":"2023-09-28","arxiv_id":"2309.16148","repositories_listed":0,"syntology":null},{"url":null,"slug":"videodirectorgpt-consistent-multi-scene-video","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","date":"2023-09-26","arxiv_id":"2309.15091","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-power-of-sound-tpos-audio-reactive-video","title":"The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion","date":"2023-09-08","arxiv_id":"2309.04509","repositories_listed":0,"syntology":null},{"url":null,"slug":"renaissance-a-survey-into-ai-text-to-image","title":"RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model","date":"2023-09-02","arxiv_id":"2309.00810","repositories_listed":0,"syntology":null},{"url":null,"slug":"videogen-a-reference-guided-latent-diffusion","title":"VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation","date":"2023-09-01","arxiv_id":"2309.00398","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-vision-and-language-through-graphs","title":"Explaining Vision and Language through Graphs of Events in Space and Time","date":"2023-08-29","arxiv_id":"2309.08612","repositories_listed":0,"syntology":null},{"url":null,"slug":"magicavatar-multimodal-avatar-generation-and","title":"MagicAvatar: Multimodal Avatar Generation and Animation","date":"2023-08-28","arxiv_id":"2308.14748","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-dynamics-aware-text-to-video","title":"Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs","date":"2023-08-26","arxiv_id":"2308.13812","repositories_listed":0,"syntology":null},{"url":null,"slug":"apla-additional-perturbation-for-latent-noise","title":"APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistency","date":"2023-08-24","arxiv_id":"2308.12605","repositories_listed":0,"syntology":null},{"url":null,"slug":"hamiltonian-gan","title":"Hamiltonian GAN","date":"2023-08-22","arxiv_id":"2308.11216","repositories_listed":0,"syntology":null},{"url":null,"slug":"simda-simple-diffusion-adapter-for-efficient","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","date":"2023-08-18","arxiv_id":"2308.09710","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-stream-diffusion-net-for-text-to-video","title":"Dual-Stream Diffusion Net for Text-to-Video Generation","date":"2023-08-16","arxiv_id":"2308.08316","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobilevidfactory-automatic-diffusion-based","title":"MobileVidFactory: Automatic Diffusion-Based Social Media Video Generation for Mobile Devices from Text","date":"2023-07-31","arxiv_id":"2307.16371","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-semantic-perceptual-listener","title":"Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline","date":"2023-07-19","arxiv_id":"2307.09821","repositories_listed":0,"syntology":null},{"url":null,"slug":"ada-tta-towards-adaptive-high-quality-text-to","title":"Ada-TTA: Towards Adaptive High-Quality Text-to-Talking Avatar Synthesis","date":"2023-06-06","arxiv_id":"2306.03504","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-sample-anonymity-in-score-based","title":"Quantifying Sample Anonymity in Score-Based Generative Models with Adversarial Fingerprinting","date":"2023-06-02","arxiv_id":"2306.01363","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-your-video-customized-video-generation","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","date":"2023-06-01","arxiv_id":"2306.00943","repositories_listed":0,"syntology":null},{"url":"/paper/preserve-your-own-correlation-a-noise-prior","slug":"preserve-your-own-correlation-a-noise-prior","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","date":"2023-05-17","arxiv_id":"2305.10474","repositories_listed":0,"syntology":null},{"url":"/paper/make-an-animation-large-scale-text","slug":"make-an-animation-large-scale-text","title":"Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation","date":"2023-05-16","arxiv_id":"2305.09662","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-a-protagonist-generic-video-editing-with","title":"Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts","date":"2023-05-15","arxiv_id":"2305.08850","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-object-video-generation-from-single","title":"Multi-object Video Generation from Single Frame Layouts","date":"2023-05-06","arxiv_id":"2305.03983","repositories_listed":0,"syntology":null},{"url":null,"slug":"stylelipsync-style-based-personalized-lip","title":"StyleLipSync: Style-based Personalized Lip-sync Video Generation","date":"2023-04-30","arxiv_id":"2305.00521","repositories_listed":0,"syntology":null},{"url":null,"slug":"lamd-latent-motion-diffusion-for-video","title":"LaMD: Latent Motion Diffusion for Image-Conditional Video Generation","date":"2023-04-23","arxiv_id":"2304.11603","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-fidelity-and-freely-controllable-talking","title":"High-Fidelity and Freely Controllable Talking Head Video Generation","date":"2023-04-20","arxiv_id":"2304.10168","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-shift-latent-diffusion-with-temporal","title":"Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation","date":"2023-04-17","arxiv_id":"2304.08477","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-generation-beyond-a-single-clip","title":"Video Generation Beyond a Single Clip","date":"2023-04-15","arxiv_id":"2304.07483","repositories_listed":0,"syntology":null},{"url":null,"slug":"vidstyleode-disentangled-video-editing-via","title":"VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs","date":"2023-04-12","arxiv_id":"2304.06020","repositories_listed":0,"syntology":null},{"url":null,"slug":"qualitative-failures-of-image-generation","title":"Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes","date":"2023-03-29","arxiv_id":"2304.06470","repositories_listed":0,"syntology":null},{"url":null,"slug":"nuwa-xl-diffusion-over-diffusion-for","title":"NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation","date":"2023-03-22","arxiv_id":"2303.12346","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-video-generation-by-learning-the","title":"Controllable Video Generation by Learning the Underlying Dynamical System with Neural ODE","date":"2023-03-09","arxiv_id":"2303.05323","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-face-video-re-enactment-using-hybrid","title":"One-Shot Face Video Re-enactment using Hybrid Latent Spaces of StyleGAN2","date":"2023-02-15","arxiv_id":"2302.07848","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-and-content-guided-video-synthesis","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","date":"2023-02-06","arxiv_id":"2302.03011","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamix-video-diffusion-models-are-general","title":"Dreamix: Video Diffusion Models are General Video Editors","date":"2023-02-02","arxiv_id":"2302.01329","repositories_listed":0,"syntology":null},{"url":null,"slug":"scenescape-text-driven-consistent-scene-1","title":"SceneScape: Text-Driven Consistent Scene Generation","date":"2023-02-02","arxiv_id":"2302.01133","repositories_listed":0,"syntology":null},{"url":"/paper/learning-universal-policies-via-text-guided","slug":"learning-universal-policies-via-text-guided","title":"Learning Universal Policies via Text-Guided Video Generation","date":"2023-01-31","arxiv_id":"2302.00111","repositories_listed":0,"syntology":null},{"url":null,"slug":"regeneration-learning-a-learning-paradigm-for","title":"Regeneration Learning: A Learning Paradigm for Data Generation","date":"2023-01-21","arxiv_id":"2301.08846","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffused-heads-diffusion-models-beat-gans-on","title":"Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation","date":"2023-01-06","arxiv_id":"2301.03396","repositories_listed":0,"syntology":null},{"url":null,"slug":"sidgan-high-resolution-dubbed-video","title":"SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant Learning","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recovering-surveillance-video-using-rf-cues","title":"Recovering Surveillance Video Using RF Cues","date":"2022-12-27","arxiv_id":"2212.13340","repositories_listed":0,"syntology":null},{"url":null,"slug":"pv3d-a-3d-generative-model-for-portrait-video","title":"PV3D: A 3D Generative Model for Portrait Video Generation","date":"2022-12-13","arxiv_id":"2212.06384","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-cell-video-synthesis-via-optical-flow","title":"Neural Cell Video Synthesis via Optical-Flow Diffusion","date":"2022-12-06","arxiv_id":"2212.03250","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-driven-co-speech-gesture-video","title":"Audio-Driven Co-Speech Gesture Video Generation","date":"2022-12-05","arxiv_id":"2212.02350","repositories_listed":0,"syntology":null},{"url":null,"slug":"3ddesigner-towards-photorealistic-3d-object","title":"3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models","date":"2022-11-25","arxiv_id":"2211.14108","repositories_listed":0,"syntology":null},{"url":"/paper/magicvideo-efficient-video-generation-with","slug":"magicvideo-efficient-video-generation-with","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","date":"2022-11-20","arxiv_id":"2211.11018","repositories_listed":0,"syntology":null},{"url":null,"slug":"facial-expression-video-generation-based-on-1","title":"Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN","date":"2022-10-20","arxiv_id":"2210.11182","repositories_listed":0,"syntology":null},{"url":null,"slug":"deephs-hdrvideo-deep-high-speed-high-dynamic","title":"DeepHS-HDRVideo: Deep High Speed High Dynamic Range Video Reconstruction","date":"2022-10-10","arxiv_id":"2210.04429","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-plan-predict-language-guided-cognitive","title":"See, Plan, Predict: Language-guided Cognitive Planning with Video Prediction","date":"2022-10-07","arxiv_id":"2210.03825","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-driven-video-prediction","title":"Text-driven Video Prediction","date":"2022-10-06","arxiv_id":"2210.02872","repositories_listed":0,"syntology":null},{"url":"/paper/imagen-video-high-definition-video-generation","slug":"imagen-video-high-definition-video-generation","title":"Imagen Video: High Definition Video Generation with Diffusion Models","date":"2022-10-05","arxiv_id":"2210.02303","repositories_listed":0,"syntology":null},{"url":null,"slug":"autolv-automatic-lecture-video-generator","title":"AutoLV: Automatic Lecture Video Generator","date":"2022-09-19","arxiv_id":"2209.08795","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuously-controllable-facial-expression","title":"Continuously Controllable Facial Expression Editing in Talking Face Videos","date":"2022-09-17","arxiv_id":"2209.08289","repositories_listed":0,"syntology":null},{"url":null,"slug":"stableface-analyzing-and-improving-motion","title":"StableFace: Analyzing and Improving Motion Stability for Talking Face Generation","date":"2022-08-29","arxiv_id":"2208.13717","repositories_listed":0,"syntology":null},{"url":null,"slug":"styletalker-one-shot-style-based-audio-driven","title":"StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation","date":"2022-08-23","arxiv_id":"2208.10922","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-harnessing-prior-structures-and","title":"Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation","date":"2022-07-08","arxiv_id":"2207.03714","repositories_listed":0,"syntology":null},{"url":"/paper/0-1-deep-neural-networks-via-block-coordinate","slug":"0-1-deep-neural-networks-via-block-coordinate","title":"0/1 Deep Neural Networks via Block Coordinate Descent","date":"2022-06-19","arxiv_id":"2206.09379","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexlip-a-controllable-text-to-lip-system","title":"FlexLip: A Controllable Text-to-Lip System","date":"2022-06-07","arxiv_id":"2206.03206","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-video-generation-for-videos-in-the-1","title":"Cascaded Video Generation for Videos In-the-Wild","date":"2022-06-01","arxiv_id":"2206.00735","repositories_listed":0,"syntology":null},{"url":null,"slug":"copy-motion-from-one-to-another-fake-motion","title":"Copy Motion From One to Another: Fake Motion Video Generation","date":"2022-05-03","arxiv_id":"2205.01373","repositories_listed":0,"syntology":null},{"url":null,"slug":"sound-guided-semantic-video-generation","title":"Sound-Guided Semantic Video Generation","date":"2022-04-20","arxiv_id":"2204.09273","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-video-generation-through-global","title":"Controllable Video Generation through Global and Local Motion Dynamics","date":"2022-04-13","arxiv_id":"2204.06558","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-neural-textures-generating-talking","title":"Dynamic Neural Textures: Generating Talking-Face Videos with Continuously Controllable Expressions","date":"2022-04-13","arxiv_id":"2204.06180","repositories_listed":0,"syntology":null},{"url":null,"slug":"v3gan-decomposing-background-foreground-and","title":"V3GAN: Decomposing Background, Foreground and Motion for Video Generation","date":"2022-03-26","arxiv_id":"2203.14074","repositories_listed":0,"syntology":null},{"url":null,"slug":"transframer-arbitrary-frame-prediction-with","title":"Transframer: Arbitrary Frame Prediction with Generative Models","date":"2022-03-17","arxiv_id":"2203.09494","repositories_listed":0,"syntology":null},{"url":null,"slug":"dialoguenerf-towards-realistic-avatar-face-to","title":"DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation","date":"2022-03-15","arxiv_id":"2203.07931","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoencoding-video-latents-for-adversarial","title":"Autoencoding Video Latents for Adversarial Video Generation","date":"2022-01-18","arxiv_id":"2201.06888","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-driven-talking-face-video-generation-1","title":"Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels","date":"2022-01-16","arxiv_id":"2201.05986","repositories_listed":0,"syntology":null},{"url":null,"slug":"unpaired-cartoon-image-synthesis-via-gated","title":"Unpaired Cartoon Image Synthesis via Gated Cycle Mapping","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-time-video-generation-via-learning","title":"Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE","date":"2021-12-21","arxiv_id":"2112.10960","repositories_listed":0,"syntology":null},{"url":null,"slug":"layered-controllable-video-generation","title":"Layered Controllable Video Generation","date":"2021-11-24","arxiv_id":"2111.12747","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-content-swapping-using-gan","title":"Video Content Swapping Using GAN","date":"2021-11-21","arxiv_id":"2111.10916","repositories_listed":0,"syntology":null},{"url":null,"slug":"xp-gan-unsupervised-multi-object-controllable","title":"Xp-GAN: Unsupervised Multi-object Controllable Video Generation","date":"2021-11-19","arxiv_id":"2111.10233","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-comes-dancing-with-collaborative","title":"Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis","date":"2021-10-27","arxiv_id":"2110.14147","repositories_listed":0,"syntology":null},{"url":null,"slug":"vida-man-visual-dialog-with-digital-humans","title":"ViDA-MAN: Visual Dialog with Digital Humans","date":"2021-10-26","arxiv_id":"2110.13384","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-video-editing-incorporating","title":"Intelligent Video Editing: Incorporating Modern Talking Face Generation Algorithms in a Video Editor","date":"2021-10-16","arxiv_id":"2110.08580","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-variational-neural-uncertainty-1","title":"A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction","date":"2021-10-06","arxiv_id":"2110.03446","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-autoencoder-self-supervised-1","title":"Video Autoencoder: self-supervised disentanglement of static 3D structure and motion","date":"2021-10-06","arxiv_id":"2110.02951","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-generative-adversarial-networks-1","title":"A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensing","date":"2021-10-01","arxiv_id":"2110.01442","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-generative-latent-variable-models-for","title":"Towards Generative Latent Variable Models for Speech","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-mocogan-for-zero-shot-video","title":"Conditional MoCoGAN for Zero-Shot Video Generation","date":"2021-09-13","arxiv_id":"2109.05864","repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-video-generation-using-neural-odes","title":"Simple Video Generation using Neural ODEs","date":"2021-09-07","arxiv_id":"2109.03292","repositories_listed":0,"syntology":null},{"url":null,"slug":"ibutter-neural-interactive-bullet-time","title":"iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Rendering","date":"2021-08-12","arxiv_id":"2108.05577","repositories_listed":0,"syntology":null}],"record_sha256":"8e085af9ccfa4eebee51a9911a6f60d73bbf59d3c8492381e526867656a3a783","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}