{"list":"other","total":73,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"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":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"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":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"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":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2105.02872","title":"Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies","created":"2021-05-06","cited_by_count":361},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283},{"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":"2007.03858","title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","created":"2020-07-08","cited_by_count":231},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199},{"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":"1903.06473","title":"DeepHuman: 3D Human Reconstruction from a Single Image","created":"2019-03-15","cited_by_count":182},{"id":"2312.02155","title":"GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis","created":"2023-12-04","cited_by_count":170},{"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":"1609.08976","title":"Variational Autoencoder for Deep Learning of Images, Labels and Captions","created":"2016-09-28","cited_by_count":137},{"id":"2204.13686","title":"HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling","created":"2022-04-28","cited_by_count":117},{"id":"2409.10695","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","created":"2024-09-16","cited_by_count":116},{"id":"2112.02789","title":"HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs","created":"2021-12-06","cited_by_count":112},{"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":"2306.09329","title":"DreamHuman: Animatable 3D Avatars from Text","created":"2023-06-15","cited_by_count":102},{"id":"2303.12791","title":"SHERF: Generalizable Human NeRF from a Single Image","created":"2023-03-22","cited_by_count":88},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"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":"2303.15108","title":"High-fidelity 3D Human Digitization from Single 2K Resolution Images","created":"2023-03-27","cited_by_count":70},{"id":"2409.16160","title":"MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling","created":"2024-09-24","cited_by_count":64},{"id":"2411.17459","title":"WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model","created":"2024-11-26","cited_by_count":57},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55},{"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":"2501.16764","title":"DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation","created":"2025-01-28","cited_by_count":50},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49},{"id":"2309.13524","title":"Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction","created":"2023-09-24","cited_by_count":42},{"id":"2405.15763","title":"FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis","created":"2024-05-24","cited_by_count":42},{"id":"2407.12777","title":"Generalizable Human Gaussians for Sparse View Synthesis","created":"2024-07-17","cited_by_count":40},{"id":"2212.02469","title":"One-shot Implicit Animatable Avatars with Model-based Priors","created":"2022-12-05","cited_by_count":38},{"id":"2310.11449","title":"DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis","created":"2023-10-17","cited_by_count":36},{"id":"2412.09349","title":"DisPose: Disentangling Pose Guidance for Controllable Human Image Animation","created":"2024-12-12","cited_by_count":35},{"id":"2410.05227","title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","created":"2024-10-07","cited_by_count":31},{"id":"2406.06050","title":"Generalizable Human Gaussians from Single-View Image","created":"2024-06-10","cited_by_count":29},{"id":"2402.17214","title":"CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization","created":"2024-02-27","cited_by_count":28},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26},{"id":"2411.17423","title":"DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters","created":"2024-11-26","cited_by_count":24},{"id":"2401.12175","title":"Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRM","created":"2024-01-22","cited_by_count":23},{"id":"2403.11878","title":"InTeX: Interactive Text-to-texture Synthesis via Unified Depth-aware Inpainting","created":"2024-03-18","cited_by_count":22},{"id":"2404.16748","title":"TELA: Text to Layer-wise 3D Clothed Human Generation","created":"2024-04-25","cited_by_count":20},{"id":"2304.04897","title":"Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling","created":"2023-04-10","cited_by_count":19},{"id":"2502.06957","title":"GAS: Generative Avatar Synthesis from a Single Image","created":"2025-02-10","cited_by_count":19},{"id":"2408.13055","title":"Atlas Gaussians Diffusion for 3D Generation","created":"2024-08-23","cited_by_count":15},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15},{"id":"2406.13099","title":"Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models","created":"2024-06-18","cited_by_count":10},{"id":"2403.16897","title":"Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text","created":"2024-03-25","cited_by_count":7},{"id":"2401.00711","title":"Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute","created":"2024-01-01","cited_by_count":6}],"next_cursor":null}