{"list":"other","total":92,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"2309.03453","title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","created":"2023-09-07","cited_by_count":645},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2306.17843","title":"Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors","created":"2023-06-30","cited_by_count":397},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385},{"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":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2303.14184","title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior","created":"2023-03-24","cited_by_count":343},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299},{"id":"2311.11284","title":"LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching","created":"2023-11-19","cited_by_count":290},{"id":"2012.09790","title":"Neural Radiance Flow for 4D View Synthesis and Video Processing","created":"2020-12-17","cited_by_count":270},{"id":"2310.08529","title":"GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models","created":"2023-10-12","cited_by_count":255},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235},{"id":"2112.08867","title":"GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation","created":"2021-12-16","cited_by_count":216},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2404.13026","title":"PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation","created":"2024-04-19","cited_by_count":191},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2312.13763","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","created":"2023-12-21","cited_by_count":169},{"id":"2311.16918","title":"RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D","created":"2023-11-28","cited_by_count":168},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144},{"id":"2411.04928","title":"DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion","created":"2024-11-07","cited_by_count":140},{"id":"2304.04968","title":"Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond","created":"2023-04-11","cited_by_count":139},{"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":"2303.07937","title":"Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation","created":"2023-03-14","cited_by_count":133},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2402.17113","title":"Transparent Image Layer Diffusion using Latent Transparency","created":"2024-02-27","cited_by_count":114},{"id":"2308.09388","title":"Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey","created":"2023-08-18","cited_by_count":109},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108},{"id":"2312.00093","title":"GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs","created":"2023-11-30","cited_by_count":97},{"id":"2311.16854","title":"A Unified Approach for Text- and Image-guided 4D Scene Generation","created":"2023-11-28","cited_by_count":82},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2404.03575","title":"DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling","created":"2024-04-04","cited_by_count":72},{"id":"2303.17905","title":"3D-aware Image Generation using 2D Diffusion Models","created":"2023-03-31","cited_by_count":69},{"id":"2403.15951","title":"MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping","created":"2024-03-23","cited_by_count":68},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65},{"id":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63},{"id":"2406.08850","title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","created":"2024-06-13","cited_by_count":59},{"id":"2410.06756","title":"DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation","created":"2024-10-09","cited_by_count":58},{"id":"2406.13527","title":"4K4DGen: Panoramic 4D Generation at 4K Resolution","created":"2024-06-19","cited_by_count":54},{"id":"2403.16993","title":"Comp4D: LLM-Guided Compositional 4D Scene Generation","created":"2024-03-25","cited_by_count":50},{"id":"2403.12962","title":"FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation","created":"2024-03-19","cited_by_count":49},{"id":"2311.08403","title":"Instant3D: Instant Text-to-3D Generation","created":"2023-11-14","cited_by_count":45},{"id":"2401.08742","title":"Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video","created":"2024-01-16","cited_by_count":44},{"id":"2406.01476","title":"DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors","created":"2024-06-03","cited_by_count":41},{"id":"2503.20785","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","created":"2025-03-26","cited_by_count":35},{"id":"2508.13154","title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","created":"2025-08-18","cited_by_count":34},{"id":"2303.15413","title":"Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation","created":"2023-03-27","cited_by_count":32},{"id":"2312.06655","title":"Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior","created":"2023-12-11","cited_by_count":32},{"id":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27},{"id":"2310.15168","title":"Ghost on the Shell: An Expressive Representation of General 3D Shapes","created":"2023-10-23","cited_by_count":24},{"id":"2311.17082","title":"DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling","created":"2023-11-28","cited_by_count":20},{"id":"2511.16671","title":"Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation","created":"2025-11-20","cited_by_count":18},{"id":"2306.11052","title":"A spatio-temporal network for video semantic segmentation in surgical videos","created":"2023-06-19","cited_by_count":17},{"id":"2512.23568","title":"ThinkGen: Generalized Thinking for Visual Generation","created":"2025-12-29","cited_by_count":13},{"id":"2310.03015","title":"Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day","created":"2023-10-04","cited_by_count":11},{"id":"2502.08377","title":"Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features","created":"2025-02-12","cited_by_count":10},{"id":"2101.09403","title":"4D Atlas: Statistical Analysis of the Spatiotemporal Variability in Longitudinal 3D Shape Data","created":"2021-01-23","cited_by_count":8},{"id":"2504.04153","title":"Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization","created":"2025-04-05","cited_by_count":5},{"id":"2311.12050","title":"3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing","created":"2023-11-18","cited_by_count":4},{"id":"2504.20054","title":"Marmot: Object-Level Self-Correction via Multi-Agent Reasoning","created":"2025-04-10","cited_by_count":3},{"id":"2408.05492","title":"ZePo: Zero-Shot Portrait Stylization with Faster Sampling","created":"2024-08-10","cited_by_count":2},{"id":"2605.01743","title":"MOC-3D: Manifold-Order Consistency for Text-to-3D Generation","created":"2026-05-03","cited_by_count":2},{"id":"2412.16717","title":"GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space","created":"2024-12-21","cited_by_count":1}],"next_cursor":null}