{"list":"other","total":88,"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"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":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"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":"2311.16493","title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","created":"2023-11-27","cited_by_count":667},{"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":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2403.12008","title":"SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion","created":"2024-03-18","cited_by_count":364},{"id":"2105.02872","title":"Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies","created":"2021-05-06","cited_by_count":361},{"id":"2305.20091","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","created":"2023-05-31","cited_by_count":350},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2203.12575","title":"NeuMan: Neural Human Radiance Field from a Single Video","created":"2022-03-23","cited_by_count":244},{"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":"2312.09228","title":"3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting","created":"2023-12-14","cited_by_count":195},{"id":"2312.02134","title":"GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians","created":"2023-12-04","cited_by_count":191},{"id":"2311.16933","title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","created":"2023-11-28","cited_by_count":175},{"id":"2206.08929","title":"TAVA: Template-free Animatable Volumetric Actors","created":"2022-06-17","cited_by_count":172},{"id":"2403.05087","title":"SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting","created":"2024-03-08","cited_by_count":172},{"id":"2312.02973","title":"GauHuman: Articulated Gaussian Splatting from Monocular Human Videos","created":"2023-12-05","cited_by_count":168},{"id":"2304.00916","title":"DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models","created":"2023-04-03","cited_by_count":154},{"id":"2311.17910","title":"HUGS: Human Gaussian Splats","created":"2023-11-29","cited_by_count":154},{"id":"2201.12792","title":"SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video","created":"2022-01-30","cited_by_count":144},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"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":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142},{"id":"2210.10036","title":"ARAH: Animatable Volume Rendering of Articulated Human SDFs","created":"2022-10-18","cited_by_count":139},{"id":"2212.10550","title":"InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds","created":"2022-12-20","cited_by_count":138},{"id":"2302.11566","title":"Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition","created":"2023-02-22","cited_by_count":134},{"id":"2311.16099","title":"GART: Gaussian Articulated Template Models","created":"2023-11-27","cited_by_count":121},{"id":"2311.08581","title":"Drivable 3D Gaussian Avatars","created":"2023-11-14","cited_by_count":120},{"id":"2203.14478","title":"Structured Local Radiance Fields for Human Avatar Modeling","created":"2022-03-28","cited_by_count":116},{"id":"2308.10899","title":"TADA! Text to Animatable Digital Avatars","created":"2023-08-21","cited_by_count":110},{"id":"2106.02019","title":"Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control","created":"2021-06-03","cited_by_count":106},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106},{"id":"2308.08545","title":"TeCH: Text-guided Reconstruction of Lifelike Clothed Humans","created":"2023-08-16","cited_by_count":104},{"id":"2312.05941","title":"ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering","created":"2023-12-10","cited_by_count":104},{"id":"2405.20674","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","created":"2024-05-31","cited_by_count":104},{"id":"2306.09329","title":"DreamHuman: Animatable 3D Avatars from Text","created":"2023-06-15","cited_by_count":102},{"id":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100},{"id":"2407.21686","title":"Expressive Whole-Body 3D Gaussian Avatar","created":"2024-07-31","cited_by_count":89},{"id":"2310.01406","title":"HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation","created":"2023-10-02","cited_by_count":88},{"id":"2304.02001","title":"MonoHuman: Animatable Human Neural Field from Monocular Video","created":"2023-04-04","cited_by_count":85},{"id":"2303.17606","title":"AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control","created":"2023-03-30","cited_by_count":84},{"id":"2305.04789","title":"AvatarReX: Real-time Expressive Full-body Avatars","created":"2023-05-08","cited_by_count":84},{"id":"2305.12529","title":"DreamWaltz: Make a Scene with Complex 3D Animatable Avatars","created":"2023-05-21","cited_by_count":82},{"id":"2311.15855","title":"SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion","created":"2023-11-27","cited_by_count":72},{"id":"2302.12237","title":"Learning Neural Volumetric Representations of Dynamic Humans in Minutes","created":"2023-02-23","cited_by_count":70},{"id":"2405.17405","title":"Human4DiT: 360-degree Human Video Generation with 4D Diffusion Transformer","created":"2024-05-27","cited_by_count":61},{"id":"2308.03610","title":"AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose","created":"2023-08-07","cited_by_count":60},{"id":"2406.12459","title":"HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors","created":"2024-06-18","cited_by_count":54},{"id":"2404.07991","title":"GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh","created":"2024-04-11","cited_by_count":51},{"id":"2304.13006","title":"PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling","created":"2023-04-25","cited_by_count":50},{"id":"2401.08742","title":"Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video","created":"2024-01-16","cited_by_count":44},{"id":"2311.09221","title":"Single-Image 3D Human Digitization with Shape-Guided Diffusion","created":"2023-11-15","cited_by_count":42},{"id":"2205.01666","title":"DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks","created":"2022-05-03","cited_by_count":38},{"id":"2306.09864","title":"AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation","created":"2023-06-16","cited_by_count":37},{"id":"2407.08414","title":"MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos","created":"2024-07-11","cited_by_count":34},{"id":"2312.05295","title":"Disentangled Clothed Avatar Generation from Text Descriptions","created":"2023-12-08","cited_by_count":33},{"id":"2507.23785","title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","created":"2025-07-31","cited_by_count":33},{"id":"2306.00547","title":"AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars","created":"2023-06-01","cited_by_count":30},{"id":"2406.06050","title":"Generalizable Human Gaussians from Single-View Image","created":"2024-06-10","cited_by_count":29},{"id":"2312.08889","title":"SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance","created":"2023-12-13","cited_by_count":24},{"id":"2404.02148","title":"Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models","created":"2024-04-02","cited_by_count":24},{"id":"2407.03204","title":"Expressive Gaussian Human Avatars from Monocular RGB Video","created":"2024-07-03","cited_by_count":21},{"id":"2404.14410","title":"Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses","created":"2024-04-22","cited_by_count":17},{"id":"2308.09705","title":"Guide3D: Create 3D Avatars from Text and Image Guidance","created":"2023-08-18","cited_by_count":10},{"id":"2210.01651","title":"SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video","created":"2022-10-04","cited_by_count":9},{"id":"2408.11357","title":"HumanCoser: Layered 3D Human Generation via Semantic-Aware Diffusion Model","created":"2024-08-21","cited_by_count":7},{"id":"2501.07104","title":"RMAvatar: Photorealistic Human Avatar Reconstruction from Monocular Video Based on Rectified Mesh-embedded Gaussians","created":"2025-01-13","cited_by_count":7},{"id":"2312.10120","title":"MVHuman: Tailoring 2D Diffusion with Multi-view Sampling For Realistic 3D Human Generation","created":"2023-12-15","cited_by_count":6},{"id":"2502.01045","title":"WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction","created":"2025-02-03","cited_by_count":6}],"next_cursor":null}