{"list":"other","total":79,"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"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":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"1610.07584","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","created":"2016-10-24","cited_by_count":558},{"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":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2303.14184","title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior","created":"2023-03-24","cited_by_count":343},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2212.06135","title":"Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion","created":"2022-12-12","cited_by_count":309},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2212.01206","title":"DiffRF: Rendering-Guided 3D Radiance Field Diffusion","created":"2022-12-02","cited_by_count":204},{"id":"2003.13989","title":"FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction","created":"2020-03-31","cited_by_count":196},{"id":"2312.09228","title":"3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting","created":"2023-12-14","cited_by_count":195},{"id":"2305.03027","title":"NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads","created":"2023-05-04","cited_by_count":194},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2302.01133","title":"SceneScape: Text-Driven Consistent Scene Generation","created":"2023-02-02","cited_by_count":160},{"id":"2212.03267","title":"NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors","created":"2022-12-06","cited_by_count":156},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2211.16431","title":"NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360{\\deg} Views","created":"2022-11-29","cited_by_count":148},{"id":"2304.12439","title":"TextMesh: Generation of Realistic 3D Meshes From Text Prompts","created":"2023-04-24","cited_by_count":135},{"id":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131},{"id":"2311.08581","title":"Drivable 3D Gaussian Avatars","created":"2023-11-14","cited_by_count":120},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112},{"id":"2011.14143","title":"i3DMM: Deep Implicit 3D Morphable Model of Human Heads","created":"2020-11-28","cited_by_count":109},{"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":"2405.11616","title":"Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention","created":"2024-05-19","cited_by_count":100},{"id":"2303.13071","title":"PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\\circ}$","created":"2023-03-23","cited_by_count":93},{"id":"2304.10261","title":"Anything-3D: Towards Single-view Anything Reconstruction in the Wild","created":"2023-04-19","cited_by_count":92},{"id":"2105.10441","title":"Driving-Signal Aware Full-Body Avatars","created":"2021-05-21","cited_by_count":81},{"id":"2304.10700","title":"Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models","created":"2023-04-21","cited_by_count":76},{"id":"2405.17251","title":"GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping","created":"2024-05-27","cited_by_count":73},{"id":"2311.15855","title":"SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion","created":"2023-11-27","cited_by_count":72},{"id":"2312.06725","title":"EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion","created":"2023-12-11","cited_by_count":72},{"id":"1709.04307","title":"Variational Autoencoders for Deforming 3D Mesh Models","created":"2017-09-13","cited_by_count":70},{"id":"2212.08062","title":"MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation","created":"2022-12-15","cited_by_count":69},{"id":"2406.18524","title":"MultiDiff: Consistent Novel View Synthesis from a Single Image","created":"2024-06-26","cited_by_count":68},{"id":"1904.00284","title":"COCO-GAN: Generation by Parts via Conditional Coordinating","created":"2019-03-30","cited_by_count":67},{"id":"2404.19110","title":"EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars","created":"2024-04-29","cited_by_count":66},{"id":"2402.05235","title":"SPAD : Spatially Aware Multiview Diffusers","created":"2024-02-07","cited_by_count":62},{"id":"1804.00586","title":"Learning Descriptor Networks for 3D Shape Synthesis and Analysis","created":"2018-04-02","cited_by_count":56},{"id":"2312.02963","title":"MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures","created":"2023-12-05","cited_by_count":54},{"id":"2404.18630","title":"4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations","created":"2024-04-29","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":"2305.13353","title":"RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars","created":"2023-05-22","cited_by_count":45},{"id":"2205.01666","title":"DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks","created":"2022-05-03","cited_by_count":38},{"id":"2404.05680","title":"SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation","created":"2024-04-08","cited_by_count":30},{"id":"2304.02013","title":"NPC: Neural Point Characters from Video","created":"2023-04-04","cited_by_count":26},{"id":"2312.13016","title":"DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis","created":"2023-12-20","cited_by_count":26},{"id":"2310.16167","title":"iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis","created":"2023-10-24","cited_by_count":20},{"id":"2404.00485","title":"DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans","created":"2024-03-30","cited_by_count":13},{"id":"2304.13681","title":"Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation","created":"2023-04-26","cited_by_count":11}],"next_cursor":null}