{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"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":"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":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"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":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"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":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","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":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264},{"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":"2305.10973","title":"Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold","created":"2023-05-18","cited_by_count":219},{"id":"2307.02421","title":"DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models","created":"2023-07-05","cited_by_count":195},{"id":"2404.12377","title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","created":"2024-04-18","cited_by_count":195},{"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":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2304.14404","title":"Motion-Conditioned Diffusion Model for Controllable Video Synthesis","created":"2023-04-27","cited_by_count":99},{"id":"2402.03908","title":"EscherNet: A Generative Model for Scalable View Synthesis","created":"2024-02-06","cited_by_count":95},{"id":"2309.07906","title":"Generative Image Dynamics","created":"2023-09-14","cited_by_count":94},{"id":"2402.02583","title":"DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing","created":"2024-02-04","cited_by_count":88},{"id":"2403.18795","title":"Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction","created":"2024-03-27","cited_by_count":56},{"id":"2409.12753","title":"DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input","created":"2024-09-19","cited_by_count":53},{"id":"2304.12467","title":"Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction","created":"2023-04-24","cited_by_count":51},{"id":"2310.07716","title":"PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection","created":"2023-10-11","cited_by_count":46},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42},{"id":"2403.19615","title":"SA-GS: Scale-Adaptive Gaussian Splatting for Training-Free Anti-Aliasing","created":"2024-03-28","cited_by_count":41},{"id":"2401.18085","title":"Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators","created":"2024-01-31","cited_by_count":39},{"id":"2403.15382","title":"DragAPart: Learning a Part-Level Motion Prior for Articulated Objects","created":"2024-03-22","cited_by_count":32},{"id":"2408.04631","title":"Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics","created":"2024-08-08","cited_by_count":28},{"id":"2210.10775","title":"TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation","created":"2022-10-19","cited_by_count":25},{"id":"2405.02386","title":"Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids","created":"2024-05-03","cited_by_count":23},{"id":"2111.12608","title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","created":"2021-11-24","cited_by_count":22},{"id":"2309.05098","title":"3D Implicit Transporter for Temporally Consistent Keypoint Discovery","created":"2023-09-10","cited_by_count":20},{"id":"2403.11273","title":"BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis","created":"2024-03-17","cited_by_count":20},{"id":"2502.14801","title":"AVD2: Accident Video Diffusion for Accident Video Description","created":"2025-02-20","cited_by_count":20},{"id":"2309.13039","title":"NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields","created":"2023-09-22","cited_by_count":16},{"id":"2312.10034","title":"SlimmeRF: Slimmable Radiance Fields","created":"2023-12-15","cited_by_count":15},{"id":"2407.06250","title":"FairDiff: Fair Segmentation with Point-Image Diffusion","created":"2024-07-08","cited_by_count":15},{"id":"2410.11236","title":"Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling","created":"2024-10-15","cited_by_count":14},{"id":"2403.12028","title":"Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detail","created":"2024-03-18","cited_by_count":12},{"id":"2404.03634","title":"PreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments","created":"2024-04-04","cited_by_count":11},{"id":"2206.01724","title":"SNAKE: Shape-aware Neural 3D Keypoint Field","created":"2022-06-03","cited_by_count":10},{"id":"2503.02918","title":"Straight-Line Diffusion Model for Efficient 3D Molecular Generation","created":"2025-03-04","cited_by_count":8},{"id":"2403.09638","title":"SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis","created":"2024-03-14","cited_by_count":7},{"id":"2410.08181","title":"RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image","created":"2024-10-10","cited_by_count":7},{"id":"2412.02693","title":"Diffusion-based Visual Anagram as Multi-task Learning","created":"2024-12-03","cited_by_count":6}],"next_cursor":null}