{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285},{"id":"2004.03805","title":"State of the Art on Neural Rendering","created":"2020-04-08","cited_by_count":278},{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235},{"id":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176},{"id":"2211.12499","title":"Instant Volumetric Head Avatars","created":"2022-11-22","cited_by_count":159},{"id":"1905.00824","title":"Single Image Portrait Relighting","created":"2019-05-02","cited_by_count":152},{"id":"2312.06640","title":"Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution","created":"2023-12-11","cited_by_count":132},{"id":"2311.12052","title":"MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion","created":"2023-11-18","cited_by_count":117},{"id":"2110.15678","title":"A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis","created":"2021-10-29","cited_by_count":72},{"id":"2209.10510","title":"Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation","created":"2022-09-21","cited_by_count":67},{"id":"2402.18848","title":"SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting","created":"2024-02-29","cited_by_count":67},{"id":"2407.07667","title":"VEnhancer: Generative Space-Time Enhancement for Video Generation","created":"2024-07-10","cited_by_count":64},{"id":"2106.13299","title":"Free-viewpoint Indoor Neural Relighting from Multi-view Stereo","created":"2021-06-24","cited_by_count":50},{"id":"2203.16681","title":"Face Relighting with Geometrically Consistent Shadows","created":"2022-03-30","cited_by_count":43},{"id":"2410.24223","title":"URAvatar: Universal Relightable Gaussian Codec Avatars","created":"2024-10-31","cited_by_count":43},{"id":"2005.08925","title":"Portrait Shadow Manipulation","created":"2020-05-18","cited_by_count":42},{"id":"2104.00825","title":"Towards High Fidelity Face Relighting with Realistic Shadows","created":"2021-04-02","cited_by_count":42},{"id":"2311.16567","title":"MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices","created":"2023-11-28","cited_by_count":42},{"id":"2201.04873","title":"VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting","created":"2022-01-13","cited_by_count":37},{"id":"2209.09475","title":"Revisiting Image Pyramid Structure for High Resolution Salient Object Detection","created":"2022-09-20","cited_by_count":36},{"id":"2403.09632","title":"Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image","created":"2024-03-14","cited_by_count":32},{"id":"2204.03648","title":"SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage","created":"2022-04-07","cited_by_count":30},{"id":"2204.09341","title":"OutCast: Outdoor Single-image Relighting with Cast Shadows","created":"2022-04-20","cited_by_count":30},{"id":"2410.18355","title":"Real-time 3D-aware Portrait Video Relighting","created":"2024-10-24","cited_by_count":21},{"id":"2303.15437","title":"FaceLit: Neural 3D Relightable Faces","created":"2023-03-27","cited_by_count":20},{"id":"2402.04101","title":"VRMM: A Volumetric Relightable Morphable Head Model","created":"2024-02-06","cited_by_count":19},{"id":"2403.01800","title":"AtomoVideo: High Fidelity Image-to-Video Generation","created":"2024-03-04","cited_by_count":12},{"id":"2305.04745","title":"Controllable Light Diffusion for Portraits","created":"2023-05-08","cited_by_count":11},{"id":"2408.13922","title":"COMPOSE: Comprehensive Portrait Shadow Editing","created":"2024-08-25","cited_by_count":6},{"id":"2404.09918","title":"EdgeRelight360: Text-Conditioned 360-Degree HDR Image Generation for Real-Time On-Device Video Portrait Relighting","created":"2024-04-15","cited_by_count":5},{"id":"2305.11321","title":"JoIN: Joint GANs Inversion for Intrinsic Image Decomposition","created":"2023-05-18","cited_by_count":4}],"next_cursor":null}