{"list":"other","total":82,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"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":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"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":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"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":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2209.11163","title":"GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images","created":"2022-09-22","cited_by_count":446},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2311.07885","title":"One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion","created":"2023-11-14","cited_by_count":283},{"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":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185},{"id":"2412.21059","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","created":"2024-12-30","cited_by_count":156},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153},{"id":"1707.08347","title":"RankIQA: Learning from Rankings for No-reference Image Quality Assessment","created":"2017-07-26","cited_by_count":151},{"id":"2008.02312","title":"Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs","created":"2020-08-05","cited_by_count":151},{"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":"2305.18766","title":"HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance","created":"2023-05-30","cited_by_count":110},{"id":"2310.03020","title":"Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models","created":"2023-10-04","cited_by_count":79},{"id":"2403.02234","title":"3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors","created":"2024-03-04","cited_by_count":74},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63},{"id":"2207.09446","title":"ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model","created":"2022-07-19","cited_by_count":62},{"id":"2401.09050","title":"Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior","created":"2024-01-17","cited_by_count":60},{"id":"2006.00497","title":"Inferring Point Cloud Quality via Graph Similarity","created":"2020-05-31","cited_by_count":58},{"id":"2310.02977","title":"T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation","created":"2023-10-04","cited_by_count":57},{"id":"2403.14613","title":"DreamReward: Text-to-3D Generation with Human Preference","created":"2024-03-21","cited_by_count":56},{"id":"2407.04699","title":"LaRa: Efficient Large-Baseline Radiance Fields","created":"2024-07-05","cited_by_count":55},{"id":"2311.08403","title":"Instant3D: Instant Text-to-3D Generation","created":"2023-11-14","cited_by_count":45},{"id":"2412.18150","title":"EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation","created":"2024-12-24","cited_by_count":39},{"id":"2112.02851","title":"No-Reference Point Cloud Quality Assessment via Domain Adaptation","created":"2021-12-06","cited_by_count":38},{"id":"2407.02040","title":"ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation","created":"2024-07-02","cited_by_count":27},{"id":"2403.09236","title":"Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraph","created":"2024-03-14","cited_by_count":22},{"id":"2403.09140","title":"Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior","created":"2024-03-14","cited_by_count":20},{"id":"2406.18462","title":"GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality","created":"2024-06-26","cited_by_count":18},{"id":"2407.14197","title":"A Benchmark for Gaussian Splatting Compression and Quality Assessment Study","created":"2024-07-19","cited_by_count":16},{"id":"2402.02972","title":"Retrieval-Augmented Score Distillation for Text-to-3D Generation","created":"2024-02-05","cited_by_count":14},{"id":"2402.18842","title":"ViewFusion: Towards Multi-View Consistency via Interpolated Denoising","created":"2024-02-29","cited_by_count":14},{"id":"2403.10066","title":"Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment","created":"2024-03-15","cited_by_count":14},{"id":"2405.09431","title":"A Survey On Text-to-3D Contents Generation In The Wild","created":"2024-05-15","cited_by_count":14},{"id":"2412.09997","title":"GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark","created":"2024-12-13","cited_by_count":12},{"id":"2308.01940","title":"TSMD: A Database for Static Color Mesh Quality Assessment Study","created":"2023-08-03","cited_by_count":11},{"id":"2406.08488","title":"ICE-G: Image Conditional Editing of 3D Gaussian Splats","created":"2024-06-12","cited_by_count":11},{"id":"2309.15675","title":"SJTU-TMQA: A quality assessment database for static mesh with texture map","created":"2023-09-27","cited_by_count":10},{"id":"2407.06516","title":"VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving","created":"2024-07-09","cited_by_count":9},{"id":"2307.01567","title":"Once-Training-All-Fine: No-Reference Point Cloud Quality Assessment via Domain-relevance Degradation Description","created":"2023-07-04","cited_by_count":8},{"id":"2410.21299","title":"TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt","created":"2024-10-16","cited_by_count":8},{"id":"2412.11170","title":"Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation","created":"2024-12-15","cited_by_count":8},{"id":"2501.10071","title":"CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment","created":"2025-01-17","cited_by_count":7},{"id":"2409.07236","title":"3DGCQA: A Quality Assessment Database for 3D AI-Generated Contents","created":"2024-09-11","cited_by_count":6},{"id":"2308.04928","title":"GeodesicPSIM: Predicting the Quality of Static Mesh with Texture Map via Geodesic Patch Similarity","created":"2023-08-09","cited_by_count":4},{"id":"2502.16915","title":"Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model","created":"2025-02-24","cited_by_count":2},{"id":"2505.20107","title":"Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning","created":"2025-05-26","cited_by_count":2}],"next_cursor":null}