{"total":254,"rows":[{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025,"area":"wm"},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290,"area":"diffusion"},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2210.06978","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","created":"2022-10-12","cited_by_count":553,"area":"diffusion"},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513,"area":null},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506,"area":null},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385,"area":null},{"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,"area":"diffusion"},{"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,"area":"diffusion"},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334,"area":null},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299,"area":null},{"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,"area":"diffusion"},{"id":"2203.13333","title":"CLIP-Mesh: Generating textured meshes from text using pretrained image-text models","created":"2022-03-24","cited_by_count":281,"area":null},{"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,"area":"diffusion"},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246,"area":null},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245,"area":null},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228,"area":null},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205,"area":null},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"area":null},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185,"area":null},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184,"area":null},{"id":"2303.05371","title":"3DGen: Triplane Latent Diffusion for Textured Mesh Generation","created":"2023-03-09","cited_by_count":183,"area":"diffusion"},{"id":"2310.16818","title":"DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior","created":"2023-10-25","cited_by_count":158,"area":"diffusion"},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156,"area":"diffusion"},{"id":"2304.00916","title":"DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models","created":"2023-04-03","cited_by_count":154,"area":"diffusion"},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154,"area":"diffusion"},{"id":"2212.14704","title":"Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models","created":"2022-12-28","cited_by_count":151,"area":"diffusion"},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"area":null},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"area":null},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"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,"area":"diffusion"},{"id":"2305.04461","title":"Locally Attentional SDF Diffusion for Controllable 3D Shape Generation","created":"2023-05-08","cited_by_count":130,"area":null},{"id":"2212.03293","title":"Diffusion-SDF: Text-to-Shape via Voxelized Diffusion","created":"2022-12-06","cited_by_count":128,"area":null},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127,"area":null},{"id":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127,"area":"diffusion"},{"id":"2506.16504","title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","created":"2025-06-19","cited_by_count":125,"area":"diffusion"},{"id":"2212.01558","title":"PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models","created":"2022-12-03","cited_by_count":118,"area":null},{"id":"2303.12048","title":"Vox-E: Text-guided Voxel Editing of 3D Objects","created":"2023-03-21","cited_by_count":115,"area":"diffusion"},{"id":"2308.10899","title":"TADA! Text to Animatable Digital Avatars","created":"2023-08-21","cited_by_count":110,"area":null},{"id":"2404.07199","title":"RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion","created":"2024-04-10","cited_by_count":109,"area":"diffusion"},{"id":"2306.09329","title":"DreamHuman: Animatable 3D Avatars from Text","created":"2023-06-15","cited_by_count":102,"area":null},{"id":"2310.12945","title":"3D-GPT: Procedural 3D Modeling with Large Language Models","created":"2023-10-19","cited_by_count":95,"area":null},{"id":"2304.13348","title":"TextDeformer: Geometry Manipulation using Text Guidance","created":"2023-04-26","cited_by_count":94,"area":null},{"id":"2403.06738","title":"V3D: Video Diffusion Models are Effective 3D Generators","created":"2024-03-11","cited_by_count":89,"area":"diffusion"},{"id":"2310.01406","title":"HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation","created":"2023-10-02","cited_by_count":88,"area":"diffusion"},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87,"area":null},{"id":"2310.13772","title":"TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models","created":"2023-10-20","cited_by_count":87,"area":"diffusion"},{"id":"2505.07747","title":"Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets","created":"2025-05-12","cited_by_count":87,"area":"diffusion"},{"id":"2311.12891","title":"Text-Guided Texturing by Synchronized Multi-View Diffusion","created":"2023-11-21","cited_by_count":86,"area":null},{"id":"2210.11277","title":"TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition","created":"2022-10-20","cited_by_count":83,"area":null},{"id":"2305.07304","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","created":"2023-05-12","cited_by_count":83,"area":"mllm"},{"id":"2312.06644","title":"AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes","created":"2023-12-11","cited_by_count":82,"area":"wm"},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77,"area":null},{"id":"2303.13450","title":"Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes","created":"2023-03-23","cited_by_count":75,"area":null},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68,"area":null},{"id":"2212.00842","title":"3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models","created":"2022-12-01","cited_by_count":67,"area":"diffusion"},{"id":"2312.11461","title":"GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning","created":"2023-12-18","cited_by_count":63,"area":null},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63,"area":null},{"id":"2207.09446","title":"ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model","created":"2022-07-19","cited_by_count":62,"area":null},{"id":"2308.03610","title":"AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose","created":"2023-08-07","cited_by_count":60,"area":null},{"id":"2303.13843","title":"CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout","created":"2023-03-24","cited_by_count":57,"area":"diffusion"},{"id":"2209.15172","title":"Understanding Pure CLIP Guidance for Voxel Grid NeRF Models","created":"2022-09-30","cited_by_count":56,"area":null},{"id":"2205.08535","title":"AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars","created":"2022-05-17","cited_by_count":55,"area":null},{"id":"2303.00304","title":"Renderable Neural Radiance Map for Visual Navigation","created":"2023-03-01","cited_by_count":51,"area":null},{"id":"2306.03038","title":"HeadSculpt: Crafting 3D Head Avatars with Text","created":"2023-06-05","cited_by_count":49,"area":"diffusion"},{"id":"2312.08985","title":"OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers","created":"2023-12-14","cited_by_count":47,"area":null},{"id":"2211.01427","title":"CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language","created":"2022-11-02","cited_by_count":46,"area":null},{"id":"2210.15929","title":"Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training","created":"2022-10-28","cited_by_count":45,"area":null},{"id":"2311.08403","title":"Instant3D: Instant Text-to-3D Generation","created":"2023-11-14","cited_by_count":45,"area":null},{"id":"2403.09675","title":"Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases","created":"2024-02-05","cited_by_count":45,"area":null},{"id":"2512.03052","title":"LATTICE: Democratize High-Fidelity 3D Generation at Scale","created":"2025-11-24","cited_by_count":44,"area":null},{"id":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","cited_by_count":44,"area":null},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2311.17907","title":"CG3D: Compositional Generation for Text-to-3D via Gaussian Splatting","created":"2023-11-29","cited_by_count":42,"area":"diffusion"},{"id":"2210.11603","title":"3DALL-E: Integrating Text-to-Image AI in 3D Design Workflows","created":"2022-10-20","cited_by_count":41,"area":null},{"id":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"area":null},{"id":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41,"area":"diffusion"},{"id":"2403.13470","title":"Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion","created":"2024-03-20","cited_by_count":40,"area":"wm"},{"id":"2307.13908","title":"Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation","created":"2023-07-26","cited_by_count":39,"area":"diffusion"},{"id":"2309.07125","title":"Text-Guided Generation and Editing of Compositional 3D Avatars","created":"2023-09-13","cited_by_count":39,"area":null},{"id":"2311.17618","title":"ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model","created":"2023-11-29","cited_by_count":39,"area":"mllm"},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37,"area":null},{"id":"2308.02874","title":"Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation","created":"2023-08-05","cited_by_count":36,"area":"diffusion"},{"id":"2202.06079","title":"Text and Image Guided 3D Avatar Generation and Manipulation","created":"2022-02-12","cited_by_count":35,"area":null},{"id":"2411.02336","title":"MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D","created":"2024-11-04","cited_by_count":34,"area":null},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33,"area":null},{"id":"2312.04424","title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","created":"2023-12-07","cited_by_count":33,"area":null},{"id":"2404.07984","title":"View Selection for 3D Captioning via Diffusion Ranking","created":"2024-04-11","cited_by_count":32,"area":null},{"id":"2304.05868","title":"Mesh2Tex: Generating Mesh Textures from Image Queries","created":"2023-04-12","cited_by_count":31,"area":null},{"id":"2112.06390","title":"PartGlot: Learning Shape Part Segmentation from Language Reference Games","created":"2021-12-13","cited_by_count":30,"area":null},{"id":"2210.05060","title":"AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization","created":"2022-10-11","cited_by_count":28,"area":null},{"id":"2303.13273","title":"TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision","created":"2023-03-23","cited_by_count":28,"area":null},{"id":"2308.09383","title":"Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from Events","created":"2023-08-18","cited_by_count":28,"area":null},{"id":"2308.11974","title":"Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields","created":"2023-08-23","cited_by_count":28,"area":null},{"id":"2209.04145","title":"ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation","created":"2022-09-09","cited_by_count":27,"area":null},{"id":"2302.10909","title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","created":"2023-02-14","cited_by_count":27,"area":null}],"next_cursor":"100"}