{"total":151,"rows":[{"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":"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,"area":null},{"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,"area":"diffusion"},{"id":"2302.01721","title":"TEXTure: Text-Guided Texturing of 3D Shapes","created":"2023-02-03","cited_by_count":304,"area":"diffusion"},{"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":"2311.15475","title":"MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers","created":"2023-11-27","cited_by_count":259,"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":"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":"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":"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,"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":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151,"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":"2305.18766","title":"HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance","created":"2023-05-30","cited_by_count":110,"area":"diffusion"},{"id":"2306.05178","title":"SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions","created":"2023-06-08","cited_by_count":110,"area":"diffusion"},{"id":"2308.10899","title":"TADA! Text to Animatable Digital Avatars","created":"2023-08-21","cited_by_count":110,"area":null},{"id":"2402.07207","title":"GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting","created":"2024-02-11","cited_by_count":109,"area":null},{"id":"2311.16973","title":"DemoFusion: Democratising High-Resolution Image Generation With No $$$","created":"2023-11-24","cited_by_count":107,"area":null},{"id":"2312.00093","title":"GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs","created":"2023-11-30","cited_by_count":97,"area":"diffusion"},{"id":"2310.12945","title":"3D-GPT: Procedural 3D Modeling with Large Language Models","created":"2023-10-19","cited_by_count":95,"area":null},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87,"area":null},{"id":"2302.03665","title":"HumanMAC: Masked Motion Completion for Human Motion Prediction","created":"2023-02-07","cited_by_count":81,"area":null},{"id":"2303.10735","title":"SKED: Sketch-guided Text-based 3D Editing","created":"2023-03-19","cited_by_count":73,"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":"2305.06131","title":"Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era","created":"2023-05-10","cited_by_count":61,"area":null},{"id":"2404.03736","title":"SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer","created":"2024-04-04","cited_by_count":61,"area":null},{"id":"2312.01305","title":"ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models","created":"2023-12-03","cited_by_count":58,"area":"diffusion"},{"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":"2310.02977","title":"T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation","created":"2023-10-04","cited_by_count":57,"area":"diffusion"},{"id":"2410.19657","title":"DiffGS: Functional Gaussian Splatting Diffusion","created":"2024-10-25","cited_by_count":51,"area":"diffusion"},{"id":"2302.03791","title":"How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control","created":"2023-02-07","cited_by_count":50,"area":"diffusion"},{"id":"2305.14330","title":"DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation","created":"2023-05-23","cited_by_count":49,"area":null},{"id":"2306.03038","title":"HeadSculpt: Crafting 3D Head Avatars with Text","created":"2023-06-05","cited_by_count":49,"area":"diffusion"},{"id":"2311.14960","title":"Point Cloud Pre-training with Diffusion Models","created":"2023-11-25","cited_by_count":47,"area":"diffusion"},{"id":"2312.08754","title":"UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation","created":"2023-12-14","cited_by_count":47,"area":"diffusion"},{"id":"2403.19655","title":"GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling","created":"2024-03-28","cited_by_count":45,"area":null},{"id":"2405.18525","title":"REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment","created":"2024-05-28","cited_by_count":45,"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":"2403.13470","title":"Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion","created":"2024-03-20","cited_by_count":40,"area":"wm"},{"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":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2407.06191","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","created":"2024-07-08","cited_by_count":35,"area":null},{"id":"2408.10195","title":"SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views","created":"2024-08-19","cited_by_count":35,"area":"diffusion"},{"id":"2502.11612","title":"Maximum Entropy Reinforcement Learning with Diffusion Policy","created":"2025-02-17","cited_by_count":34,"area":"diffusion"},{"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":"2407.10738","title":"AccDiffusion: An Accurate Method for Higher-Resolution Image Generation","created":"2024-07-15","cited_by_count":33,"area":null},{"id":"2408.03400","title":"Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey","created":"2024-08-06","cited_by_count":32,"area":"diffusion"},{"id":"2506.09982","title":"AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation","created":"2025-06-11","cited_by_count":32,"area":null},{"id":"2306.03414","title":"DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views","created":"2023-06-06","cited_by_count":31,"area":"diffusion"},{"id":"2311.16917","title":"UGG: Unified Generative Grasping","created":"2023-11-28","cited_by_count":30,"area":null},{"id":"2409.14316","title":"MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views","created":"2024-09-22","cited_by_count":29,"area":null},{"id":"2312.02719","title":"A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling","created":"2023-12-03","cited_by_count":28,"area":"diffusion"},{"id":"2402.18490","title":"TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding","created":"2024-02-28","cited_by_count":27,"area":null},{"id":"2310.13545","title":"ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection","created":"2023-10-20","cited_by_count":25,"area":"diffusion"},{"id":"2401.11067","title":"Make-A-Shape: a Ten-Million-scale 3D Shape Model","created":"2024-01-20","cited_by_count":25,"area":null},{"id":"2402.00627","title":"CapHuman: Capture Your Moments in Parallel Universes","created":"2024-02-01","cited_by_count":22,"area":null},{"id":"2312.01663","title":"Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training","created":"2023-12-04","cited_by_count":21,"area":null},{"id":"2305.11870","title":"Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models","created":"2023-05-19","cited_by_count":20,"area":"diffusion"},{"id":"2310.02712","title":"ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF","created":"2023-10-04","cited_by_count":20,"area":"diffusion"},{"id":"2305.16411","title":"ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image","created":"2023-05-25","cited_by_count":18,"area":"diffusion"},{"id":"2311.01734","title":"Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training","created":"2023-11-03","cited_by_count":18,"area":null},{"id":"2406.18462","title":"GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality","created":"2024-06-26","cited_by_count":18,"area":null},{"id":"2305.15808","title":"Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback","created":"2023-05-25","cited_by_count":17,"area":null},{"id":"2310.10624","title":"DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing","created":"2023-10-16","cited_by_count":17,"area":"diffusion"},{"id":"2405.17859","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","created":"2024-05-28","cited_by_count":17,"area":null},{"id":"2407.12684","title":"4Dynamic: Text-to-4D Generation with Hybrid Priors","created":"2024-07-17","cited_by_count":15,"area":"diffusion"},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2601.14253","title":"Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis","created":"2026-01-20","cited_by_count":15,"area":null},{"id":"2307.16605","title":"VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation","created":"2023-07-28","cited_by_count":14,"area":null},{"id":"2308.04052","title":"The Five-Dollar Model: Generating Game Maps and Sprites from Sentence Embeddings","created":"2023-08-08","cited_by_count":14,"area":null},{"id":"2410.05591","title":"TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation","created":"2024-10-08","cited_by_count":14,"area":"diffusion"},{"id":"2309.03599","title":"Chasing Consistency in Text-to-3D Generation from a Single Image","created":"2023-09-07","cited_by_count":13,"area":null},{"id":"2401.17603","title":"Topology-Aware Latent Diffusion for 3D Shape Generation","created":"2024-01-31","cited_by_count":13,"area":"diffusion"},{"id":"2403.13289","title":"Text-to-3D Shape Generation","created":"2024-03-20","cited_by_count":13,"area":null},{"id":"2406.04253","title":"A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generation","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2307.12980","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","created":"2023-07-24","cited_by_count":12,"area":"mllm"},{"id":"2312.11923","title":"IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2404.03042","title":"AWOL: Analysis WithOut synthesis using Language","created":"2024-04-03","cited_by_count":12,"area":null},{"id":"2306.06212","title":"Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptions","created":"2023-06-09","cited_by_count":11,"area":null},{"id":"2411.16820","title":"DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2308.09705","title":"Guide3D: Create 3D Avatars from Text and Image Guidance","created":"2023-08-18","cited_by_count":10,"area":"diffusion"},{"id":"2312.12090","title":"GazeMoDiff: Gaze-guided Diffusion Model for Stochastic Human Motion Prediction","created":"2023-12-19","cited_by_count":10,"area":"diffusion"},{"id":"2411.08017","title":"Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings","created":"2024-11-12","cited_by_count":10,"area":"diffusion"},{"id":"2512.10949","title":"Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2305.02594","title":"Multimodal-driven Talking Face Generation via a Unified Diffusion-based Generator","created":"2023-05-04","cited_by_count":9,"area":"diffusion"},{"id":"2309.11281","title":"Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates","created":"2023-09-20","cited_by_count":9,"area":null},{"id":"2312.00375","title":"Text-Guided 3D Face Synthesis -- From Generation to Editing","created":"2023-12-01","cited_by_count":9,"area":"diffusion"},{"id":"2408.15660","title":"Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas","created":"2024-08-28","cited_by_count":9,"area":"diffusion"},{"id":"2412.09545","title":"SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing","created":"2024-12-12","cited_by_count":9,"area":"diffusion"},{"id":"2512.01850","title":"Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching","created":"2025-12-01","cited_by_count":9,"area":"diffusion"},{"id":"2305.14598","title":"Vision + Language Applications: A Survey","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2403.00372","title":"HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation","created":"2024-03-01","cited_by_count":8,"area":null},{"id":"2403.11990","title":"GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation","created":"2024-03-18","cited_by_count":8,"area":null},{"id":"2412.11170","title":"Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation","created":"2024-12-15","cited_by_count":8,"area":null},{"id":"2301.09091","title":"BallGAN: 3D-aware Image Synthesis with a Spherical Background","created":"2023-01-22","cited_by_count":7,"area":null},{"id":"2408.11357","title":"HumanCoser: Layered 3D Human Generation via Semantic-Aware Diffusion Model","created":"2024-08-21","cited_by_count":7,"area":"diffusion"},{"id":"2302.11710","title":"Controlled and Conditional Text to Image Generation with Diffusion Prior","created":"2023-02-23","cited_by_count":6,"area":"diffusion"},{"id":"2312.02647","title":"TPA3D: Triplane Attention for Fast Text-to-3D Generation","created":"2023-12-05","cited_by_count":6,"area":"diffusion"}],"next_cursor":"100"}