{"list":"other","total":105,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"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":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2004.04572","title":"ARCH: Animatable Reconstruction of Clothed Humans","created":"2020-04-08","cited_by_count":257},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"2105.01859","title":"Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors","created":"2021-05-05","cited_by_count":246},{"id":"2203.12575","title":"NeuMan: Neural Human Radiance Field from a Single Video","created":"2022-03-23","cited_by_count":244},{"id":"1803.04758","title":"Video Based Reconstruction of 3D People Models","created":"2018-03-13","cited_by_count":238},{"id":"2102.06199","title":"A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose","created":"2021-02-11","cited_by_count":233},{"id":"2007.03858","title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","created":"2020-07-08","cited_by_count":231},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"id":"2406.19680","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","created":"2024-06-28","cited_by_count":198},{"id":"2104.03110","title":"Neural Articulated Radiance Field","created":"2021-04-07","cited_by_count":196},{"id":"2108.07845","title":"ARCH++: Animation-Ready Clothed Human Reconstruction Revisited","created":"2021-08-17","cited_by_count":174},{"id":"2312.02973","title":"GauHuman: Articulated Gaussian Splatting from Monocular Human Videos","created":"2023-12-05","cited_by_count":168},{"id":"2003.08325","title":"DeepCap: Monocular Human Performance Capture Using Weak Supervision","created":"2020-03-18","cited_by_count":162},{"id":"2305.06356","title":"HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion","created":"2023-05-10","cited_by_count":161},{"id":"2109.07448","title":"Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering","created":"2021-09-15","cited_by_count":158},{"id":"2110.13746","title":"H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion","created":"2021-10-26","cited_by_count":157},{"id":"2003.12267","title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","created":"2020-03-27","cited_by_count":150},{"id":"2201.12792","title":"SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video","created":"2022-01-30","cited_by_count":144},{"id":"2204.11823","title":"StyleGAN-Human: A Data-Centric Odyssey of Human Generation","created":"2022-04-25","cited_by_count":144},{"id":"2210.10036","title":"ARAH: Animatable Volume Rendering of Articulated Human SDFs","created":"2022-10-18","cited_by_count":139},{"id":"2007.11432","title":"Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction","created":"2020-07-22","cited_by_count":133},{"id":"2105.01794","title":"Real-time Deep Dynamic Characters","created":"2021-05-04","cited_by_count":133},{"id":"2204.08906","title":"Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing","created":"2022-04-19","cited_by_count":126},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117},{"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":"2006.08072","title":"Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction","created":"2020-06-15","cited_by_count":112},{"id":"2210.04888","title":"EVA3D: Compositional 3D Human Generation from 2D Image Collections","created":"2022-10-10","cited_by_count":111},{"id":"2106.13629","title":"Animatable Neural Radiance Fields from Monocular RGB Videos","created":"2021-06-25","cited_by_count":109},{"id":"2010.12447","title":"LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration","created":"2020-10-23","cited_by_count":108},{"id":"2307.10173","title":"DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering","created":"2023-07-19","cited_by_count":103},{"id":"2303.12791","title":"SHERF: Generalizable Human NeRF from a Single Image","created":"2023-03-22","cited_by_count":88},{"id":"2312.06704","title":"SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction","created":"2023-12-10","cited_by_count":77},{"id":"2007.13988","title":"Monocular Real-Time Volumetric Performance Capture","created":"2020-07-28","cited_by_count":74},{"id":"2303.15108","title":"High-fidelity 3D Human Digitization from Single 2K Resolution Images","created":"2023-03-27","cited_by_count":70},{"id":"2008.06872","title":"SMPLpix: Neural Avatars from 3D Human Models","created":"2020-08-16","cited_by_count":69},{"id":"2203.02910","title":"Exploring Dual-task Correlation for Pose Guided Person Image Generation","created":"2022-03-06","cited_by_count":68},{"id":"2012.01451","title":"Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction","created":"2020-12-02","cited_by_count":67},{"id":"2405.17405","title":"Human4DiT: 360-degree Human Video Generation with 4D Diffusion Transformer","created":"2024-05-27","cited_by_count":61},{"id":"2101.04104","title":"Neural Re-Rendering of Humans from a Single Image","created":"2021-01-11","cited_by_count":59},{"id":"2101.06571","title":"S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling","created":"2021-01-17","cited_by_count":59},{"id":"2406.11819","title":"MegaScenes: Scene-Level View Synthesis at Scale","created":"2024-06-17","cited_by_count":58},{"id":"2303.17368","title":"SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling","created":"2023-03-30","cited_by_count":54},{"id":"2305.00121","title":"Learning Locally Editable Virtual Humans","created":"2023-04-28","cited_by_count":54},{"id":"2406.12459","title":"HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors","created":"2024-06-18","cited_by_count":54},{"id":"2012.03796","title":"Pose-Guided Human Animation from a Single Image in the Wild","created":"2020-12-07","cited_by_count":53},{"id":"2203.16875","title":"MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images","created":"2022-03-31","cited_by_count":53},{"id":"2304.08483","title":"Text2Performer: Text-Driven Human Video Generation","created":"2023-04-17","cited_by_count":53},{"id":"2103.06902","title":"HumanGAN: A Generative Model of Humans Images","created":"2021-03-11","cited_by_count":47},{"id":"2203.01754","title":"PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence","created":"2022-03-03","cited_by_count":46},{"id":"2008.12606","title":"Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation","created":"2020-08-27","cited_by_count":43},{"id":"2212.02469","title":"One-shot Implicit Animatable Avatars with Model-based Priors","created":"2022-12-05","cited_by_count":38},{"id":"2304.03903","title":"High-Fidelity Clothed Avatar Reconstruction from a Single Image","created":"2023-04-08","cited_by_count":38},{"id":"2212.05321","title":"HumanGen: Generating Human Radiance Fields with Explicit Priors","created":"2022-12-10","cited_by_count":33},{"id":"2004.02460","title":"Robust 3D Self-portraits in Seconds","created":"2020-04-06","cited_by_count":30},{"id":"2309.01855","title":"SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Image","created":"2023-09-04","cited_by_count":30},{"id":"2406.06050","title":"Generalizable Human Gaussians from Single-View Image","created":"2024-06-10","cited_by_count":29},{"id":"2307.07754","title":"Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer","created":"2023-07-15","cited_by_count":25},{"id":"2210.00627","title":"MonoNHR: Monocular Neural Human Renderer","created":"2022-10-02","cited_by_count":15}],"next_cursor":"100"}