{"list":"other","total":85,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"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":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"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":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"1704.00090","title":"Learning to Predict Indoor Illumination from a Single Image","created":"2017-04-01","cited_by_count":161},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135},{"id":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"id":"2210.10770","title":"LaMAR: Benchmarking Localization and Mapping for Augmented Reality","created":"2022-10-19","cited_by_count":100},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94},{"id":"2305.19195","title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation","created":"2023-05-30","cited_by_count":77},{"id":"2212.03239","title":"Perspective Fields for Single Image Camera Calibration","created":"2022-12-06","cited_by_count":75},{"id":"2401.06578","title":"360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model","created":"2024-01-12","cited_by_count":58},{"id":"2305.10853","title":"LDM3D: Latent Diffusion Model for 3D","created":"2023-05-18","cited_by_count":53},{"id":"2409.06704","title":"GeoCalib: Learning Single-image Calibration with Geometric Optimization","created":"2024-09-10","cited_by_count":52},{"id":"2307.03177","title":"PanoDiffusion: 360-degree Panorama Outpainting via Diffusion","created":"2023-07-06","cited_by_count":51},{"id":"2311.13141","title":"Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models","created":"2023-11-22","cited_by_count":49},{"id":"2011.10687","title":"HDR Environment Map Estimation for Real-Time Augmented Reality","created":"2020-11-21","cited_by_count":47},{"id":"2203.14668","title":"Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation","created":"2022-03-28","cited_by_count":47},{"id":"2310.18840","title":"Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models","created":"2023-10-28","cited_by_count":47},{"id":"2308.14686","title":"360-Degree Panorama Generation from Few Unregistered NFoV Images","created":"2023-08-28","cited_by_count":42},{"id":"2410.24203","title":"DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion","created":"2024-10-31","cited_by_count":38},{"id":"2501.17162","title":"CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation","created":"2025-01-28","cited_by_count":35},{"id":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34},{"id":"2309.03467","title":"Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation","created":"2023-09-07","cited_by_count":33},{"id":"2204.07286","title":"Guided Co-Modulated GAN for 360{\\deg} Field of View Extrapolation","created":"2022-04-15","cited_by_count":32},{"id":"2412.03552","title":"Imagine360: Immersive 360 Video Generation from Perspective Anchor","created":"2024-12-04","cited_by_count":29},{"id":"2504.17788","title":"Dynamic Camera Poses and Where to Find Them","created":"2025-04-24","cited_by_count":27},{"id":"2412.11100","title":"DynamicScaler: Seamless and Scalable Video Generation for Panoramic Scenes","created":"2024-12-15","cited_by_count":24},{"id":"2412.07770","title":"From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos","created":"2024-12-10","cited_by_count":23},{"id":"2505.22016","title":"PanoWan: Lifting Diffusion Video Generation Models to 360{\\deg} with Latitude/Longitude-aware Mechanisms","created":"2025-05-28","cited_by_count":23},{"id":"2511.16825","title":"WorldGen: From Text to Traversable and Interactive 3D Worlds","created":"2025-11-20","cited_by_count":19},{"id":"2408.02157","title":"PanoFree: Tuning-Free Holistic Multi-view Image Generation with Cross-view Self-Guidance","created":"2024-08-04","cited_by_count":18},{"id":"2504.07940","title":"Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos","created":"2025-04-10","cited_by_count":16},{"id":"2509.03680","title":"LuxDiT: Lighting Estimation with Video Diffusion Transformer","created":"2025-09-03","cited_by_count":15},{"id":"2403.10044","title":"SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model","created":"2024-03-15","cited_by_count":13},{"id":"2503.16611","title":"A Recipe for Generating 3D Worlds From a Single Image","created":"2025-03-20","cited_by_count":13},{"id":"2504.11389","title":"VideoPanda: Video Panoramic Diffusion with Multi-view Attention","created":"2025-04-15","cited_by_count":13},{"id":"2505.22129","title":"What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?","created":"2025-05-28","cited_by_count":13},{"id":"2410.13832","title":"VidPanos: Generative Panoramic Videos from Casual Panning Videos","created":"2024-10-17","cited_by_count":12},{"id":"2506.17206","title":"DreamCube: 3D Panorama Generation via Multi-plane Synchronization","created":"2025-06-20","cited_by_count":12},{"id":"2503.18420","title":"Panorama Generation From NFoV Image Done Right","created":"2025-03-24","cited_by_count":11},{"id":"2308.10694","title":"Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction","created":"2023-08-21","cited_by_count":9},{"id":"2407.18207","title":"Geometry Fidelity for Spherical Images","created":"2024-07-25","cited_by_count":9},{"id":"2504.11379","title":"Omni$^2$: Unifying Omnidirectional Image Generation and Editing in an Omni Model","created":"2025-04-15","cited_by_count":9},{"id":"2505.16862","title":"Conditional Panoramic Image Generation via Masked Autoregressive Modeling","created":"2025-05-22","cited_by_count":9},{"id":"2001.02993","title":"Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry","created":"2020-01-09","cited_by_count":5},{"id":"2411.15867","title":"PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs","created":"2024-11-24","cited_by_count":4},{"id":"2506.21681","title":"TanDiT: Tangent-Plane Diffusion Transformer for High-Quality 360{\\deg} Panorama Generation","created":"2025-06-26","cited_by_count":3}],"next_cursor":null}