{"list":"other","total":97,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"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":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"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":"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":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","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":"2111.04276","title":"Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis","created":"2021-11-08","cited_by_count":460},{"id":"2011.14672","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","created":"2020-11-30","cited_by_count":307},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283},{"id":"2312.02069","title":"GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians","created":"2023-12-04","cited_by_count":260},{"id":"2004.04572","title":"ARCH: Animatable Reconstruction of Clothed Humans","created":"2020-04-08","cited_by_count":257},{"id":"2103.16507","title":"PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop","created":"2021-03-30","cited_by_count":250},{"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":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2007.03858","title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","created":"2020-07-08","cited_by_count":231},{"id":"2305.16311","title":"Break-A-Scene: Extracting Multiple Concepts from a Single Image","created":"2023-05-25","cited_by_count":231},{"id":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199},{"id":"2311.13600","title":"ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs","created":"2023-11-22","cited_by_count":194},{"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":"2409.19152","title":"MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion","created":"2024-09-27","cited_by_count":162},{"id":"2212.10550","title":"InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds","created":"2022-12-20","cited_by_count":138},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135},{"id":"2405.20343","title":"Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image","created":"2024-05-30","cited_by_count":135},{"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":"2310.19415","title":"Text-to-3D with Classifier Score Distillation","created":"2023-10-30","cited_by_count":128},{"id":"2305.15391","title":"A Neural Space-Time Representation for Text-to-Image Personalization","created":"2023-05-24","cited_by_count":123},{"id":"2401.03407","title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","created":"2024-01-07","cited_by_count":112},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112},{"id":"2308.10899","title":"TADA! Text to Animatable Digital Avatars","created":"2023-08-21","cited_by_count":110},{"id":"2311.18809","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","created":"2023-11-30","cited_by_count":109},{"id":"2308.08545","title":"TeCH: Text-guided Reconstruction of Lifelike Clothed Humans","created":"2023-08-16","cited_by_count":104},{"id":"2405.11616","title":"Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention","created":"2024-05-19","cited_by_count":100},{"id":"2310.17590","title":"Noise-Free Score Distillation","created":"2023-10-26","cited_by_count":99},{"id":"2311.17061","title":"HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting","created":"2023-11-28","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":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2303.15108","title":"High-fidelity 3D Human Digitization from Single 2K Resolution Images","created":"2023-03-27","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":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61},{"id":"2309.16668","title":"RealFill: Reference-Driven Generation for Authentic Image Completion","created":"2023-09-28","cited_by_count":59},{"id":"2305.00121","title":"Learning Locally Editable Virtual Humans","created":"2023-04-28","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":"2407.06187","title":"JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation","created":"2024-07-08","cited_by_count":52},{"id":"2501.12224","title":"TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space","created":"2025-01-21","cited_by_count":52},{"id":"2406.08475","title":"Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models","created":"2024-06-12","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":"2306.09864","title":"AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation","created":"2023-06-16","cited_by_count":37},{"id":"2412.02684","title":"AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction","created":"2024-12-03","cited_by_count":36},{"id":"2412.10209","title":"GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion","created":"2024-12-13","cited_by_count":36},{"id":"2501.09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation","created":"2025-01-16","cited_by_count":32},{"id":"2503.01610","title":"Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior","created":"2025-03-03","cited_by_count":31},{"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":"2310.10644","title":"TOSS:High-quality Text-guided Novel View Synthesis from a Single Image","created":"2023-10-16","cited_by_count":26},{"id":"2412.09618","title":"EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM","created":"2024-12-12","cited_by_count":25},{"id":"2502.01720","title":"Generating Multi-Image Synthetic Data for Text-to-Image Customization","created":"2025-02-03","cited_by_count":25},{"id":"2408.14211","title":"MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement","created":"2024-08-26","cited_by_count":24},{"id":"2311.16961","title":"HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion","created":"2023-11-28","cited_by_count":23},{"id":"2409.10141","title":"PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing","created":"2024-09-16","cited_by_count":23},{"id":"2305.11870","title":"Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models","created":"2023-05-19","cited_by_count":20},{"id":"2405.12420","title":"GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details","created":"2024-05-20","cited_by_count":19},{"id":"2412.09694","title":"Omni-ID: Holistic Identity Representation Designed for Generative Tasks","created":"2024-12-12","cited_by_count":18},{"id":"2507.13344","title":"Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models","created":"2025-07-17","cited_by_count":17},{"id":"2311.17123","title":"ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis","created":"2023-11-28","cited_by_count":16},{"id":"2405.14869","title":"PuzzleAvatar: Assembling 3D Avatars from Personal Albums","created":"2024-05-23","cited_by_count":16},{"id":"2311.15672","title":"HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained Images","created":"2023-11-27","cited_by_count":13},{"id":"2403.09326","title":"HeadEvolver: Text to Head Avatars via Expressive and Attribute-Preserving Mesh Deformation","created":"2024-03-14","cited_by_count":11},{"id":"2505.05022","title":"SOAP: Style-Omniscient Animatable Portraits","created":"2025-05-08","cited_by_count":11},{"id":"2501.14231","title":"Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images","created":"2025-01-24","cited_by_count":10},{"id":"2503.10624","title":"ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness","created":"2025-03-13","cited_by_count":9},{"id":"2506.03118","title":"HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers","created":"2025-06-03","cited_by_count":9},{"id":"2308.07415","title":"Semantify: Simplifying the Control of 3D Morphable Models using CLIP","created":"2023-08-14","cited_by_count":8},{"id":"2211.14485","title":"FastHuman: Reconstructing High-Quality Clothed Human in Minutes","created":"2022-11-26","cited_by_count":6},{"id":"2308.14740","title":"Total Selfie: Generating Full-Body Selfies","created":"2023-08-28","cited_by_count":5},{"id":"2404.03652","title":"The More You See in 2D, the More You Perceive in 3D","created":"2024-04-04","cited_by_count":5},{"id":"2409.05099","title":"DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping","created":"2024-09-08","cited_by_count":5},{"id":"2412.17290","title":"Free-viewpoint Human Animation with Pose-correlated Reference Selection","created":"2024-12-23","cited_by_count":5},{"id":"2505.06537","title":"ProFashion: Prototype-guided Fashion Video Generation with Multiple Reference Images","created":"2025-05-10","cited_by_count":5},{"id":"2204.11184","title":"MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames","created":"2022-04-24","cited_by_count":2},{"id":"2211.10098","title":"UnconFuse: Avatar Reconstruction from Unconstrained Images","created":"2022-11-18","cited_by_count":2},{"id":"2508.14892","title":"Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds","created":"2025-08-20","cited_by_count":2},{"id":"2410.23800","title":"SOAR: Self-Occluded Avatar Recovery from a Single Video In the Wild","created":"2024-10-31","cited_by_count":1}],"next_cursor":null}