{"list":"other","total":64,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"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":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"1907.10786","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","created":"2019-07-25","cited_by_count":695},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2102.02766","title":"Designing an Encoder for StyleGAN Image Manipulation","created":"2021-02-04","cited_by_count":544},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2007.06600","title":"Closed-Form Factorization of Latent Semantics in GANs","created":"2020-07-13","cited_by_count":408},{"id":"2005.09635","title":"InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs","created":"2020-05-18","cited_by_count":394},{"id":"2208.11970","title":"Understanding Diffusion Models: A Unified Perspective","created":"2022-08-25","cited_by_count":340},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2311.12092","title":"Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models","created":"2023-11-20","cited_by_count":153},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144},{"id":"2411.04928","title":"DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion","created":"2024-11-07","cited_by_count":140},{"id":"2406.10126","title":"Training-free Camera Control for Video Generation","created":"2024-06-14","cited_by_count":122},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117},{"id":"2212.08698","title":"Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models","created":"2022-12-16","cited_by_count":116},{"id":"1905.05169","title":"Zoom To Learn, Learn To Zoom","created":"2019-05-13","cited_by_count":115},{"id":"2204.07156","title":"Any-resolution Training for High-resolution Image Synthesis","created":"2022-04-14","cited_by_count":72},{"id":"2211.14108","title":"3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models","created":"2022-11-25","cited_by_count":57},{"id":"2403.18103","title":"Tutorial on Diffusion Models for Imaging and Vision","created":"2024-03-26","cited_by_count":49},{"id":"2206.12614","title":"BokehMe: When Neural Rendering Meets Classical Rendering","created":"2022-06-25","cited_by_count":48},{"id":"1905.06326","title":"Synthetic Defocus and Look-Ahead Autofocus for Casual Videography","created":"2019-05-15","cited_by_count":28},{"id":"2407.01516","title":"E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness","created":"2024-07-01","cited_by_count":25},{"id":"2410.10774","title":"Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention","created":"2024-10-14","cited_by_count":24},{"id":"2410.10802","title":"Boosting Camera Motion Control for Video Diffusion Transformers","created":"2024-10-14","cited_by_count":20},{"id":"2308.08843","title":"Dr.Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering","created":"2023-08-17","cited_by_count":19},{"id":"2212.07778","title":"Efficient Visual Computing with Camera RAW Snapshots","created":"2022-12-15","cited_by_count":18},{"id":"2402.16143","title":"Cinematographic Camera Diffusion Model","created":"2024-02-25","cited_by_count":18},{"id":"2207.08403","title":"MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects","created":"2022-07-18","cited_by_count":17},{"id":"2406.07480","title":"Image Neural Field Diffusion Models","created":"2024-06-11","cited_by_count":13},{"id":"2104.05237","title":"Neural Camera Simulators","created":"2021-04-12","cited_by_count":10},{"id":"2303.17253","title":"HDR Imaging with Spatially Varying Signal-to-Noise Ratios","created":"2023-03-30","cited_by_count":8},{"id":"2306.17367","title":"Spatially Varying Exposure with 2-by-2 Multiplexing: Optimality and Universality","created":"2023-06-30","cited_by_count":6},{"id":"2402.13490","title":"Contrastive Prompts Improve Disentanglement in Text-to-Image Diffusion Models","created":"2024-02-21","cited_by_count":4},{"id":"2405.13195","title":"CamViG: Camera Aware Image-to-Video Generation with Multimodal Transformers","created":"2024-05-21","cited_by_count":3},{"id":"2406.08924","title":"Learning Images Across Scales Using Adversarial Training","created":"2024-06-13","cited_by_count":3},{"id":"2006.02692","title":"Problems of dataset creation for light source estimation","created":"2020-06-04","cited_by_count":1}],"next_cursor":null}