{"list":"other","total":81,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2007.11571","title":"Neural Sparse Voxel Fields","created":"2020-07-22","cited_by_count":959},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"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":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"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":"2404.07191","title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","created":"2024-04-10","cited_by_count":433},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393},{"id":"2311.06214","title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","created":"2023-11-10","cited_by_count":378},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","cited_by_count":364},{"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":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"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":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2312.09147","title":"Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers","created":"2023-12-14","cited_by_count":258},{"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":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2403.05034","title":"CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model","created":"2024-03-08","cited_by_count":215},{"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":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2403.05087","title":"SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting","created":"2024-03-08","cited_by_count":172},{"id":"2312.02155","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":"2312.02973","title":"GauHuman: Articulated Gaussian Splatting from Monocular Human Videos","created":"2023-12-05","cited_by_count":168},{"id":"2308.05371","title":"Flexible Isosurface Extraction for Gradient-Based Mesh Optimization","created":"2023-08-10","cited_by_count":139},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139},{"id":"2105.05301","title":"Collaborative Regression of Expressive Bodies using Moderation","created":"2021-05-11","cited_by_count":137},{"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":"2311.17113","title":"Human Gaussian Splatting: Real-time Rendering of Animatable Avatars","created":"2023-11-28","cited_by_count":105},{"id":"2312.05941","title":"ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering","created":"2023-12-10","cited_by_count":104},{"id":"2303.12791","title":"SHERF: Generalizable Human NeRF from a Single Image","created":"2023-03-22","cited_by_count":88},{"id":"2506.05573","title":"PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers","created":"2025-06-05","cited_by_count":84},{"id":"2403.15624","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":82},{"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":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","cited_by_count":73},{"id":"2209.08776","title":"NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes","created":"2022-09-19","cited_by_count":71},{"id":"2303.15108","title":"High-fidelity 3D Human Digitization from Single 2K Resolution Images","created":"2023-03-27","cited_by_count":70},{"id":"2312.03461","title":"HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting","created":"2023-12-06","cited_by_count":70},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"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":"2406.12459","title":"HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors","created":"2024-06-18","cited_by_count":54},{"id":"2406.13527","title":"4K4DGen: Panoramic 4D Generation at 4K Resolution","created":"2024-06-19","cited_by_count":54},{"id":"2305.00942","title":"StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video","created":"2023-05-01","cited_by_count":52},{"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":"2501.16764","title":"DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation","created":"2025-01-28","cited_by_count":50},{"id":"2406.08475","title":"Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models","created":"2024-06-12","cited_by_count":44},{"id":"2408.06019","title":"HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors","created":"2024-08-12","cited_by_count":44},{"id":"2407.12777","title":"Generalizable Human Gaussians for Sparse View Synthesis","created":"2024-07-17","cited_by_count":40},{"id":"2410.14462","title":"LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes","created":"2024-10-18","cited_by_count":37},{"id":"2401.09720","title":"GaussianBody: Clothed Human Reconstruction via 3d Gaussian Splatting","created":"2024-01-18","cited_by_count":36},{"id":"2312.15258","title":"Human101: Training 100+FPS Human Gaussians in 100s from 1 View","created":"2023-12-23","cited_by_count":32},{"id":"2404.01053","title":"HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior","created":"2024-04-01","cited_by_count":31},{"id":"2304.02163","title":"GINA-3D: Learning to Generate Implicit Neural Assets in the Wild","created":"2023-04-04","cited_by_count":25},{"id":"2406.08479","title":"Real3D: Scaling Up Large Reconstruction Models with Real-World Images","created":"2024-06-12","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":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22},{"id":"2402.16607","title":"GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos","created":"2024-02-26","cited_by_count":22},{"id":"2411.11363","title":"GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views","created":"2024-11-18","cited_by_count":22},{"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":"2407.07580","title":"InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Prior","created":"2024-07-10","cited_by_count":6},{"id":"2407.14007","title":"Multi-modal Relation Distillation for Unified 3D Representation Learning","created":"2024-07-19","cited_by_count":6}],"next_cursor":null}