{"total":54,"rows":[{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"area":null},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458,"area":"diffusion"},{"id":"2212.04493","title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","created":"2022-12-08","cited_by_count":288,"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":"2203.09516","title":"AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation","created":"2022-03-17","cited_by_count":208,"area":null},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146,"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":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127,"area":"diffusion"},{"id":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104,"area":null},{"id":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70,"area":"distill"},{"id":"2303.12236","title":"SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation","created":"2023-03-21","cited_by_count":66,"area":"diffusion"},{"id":"2207.09446","title":"ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model","created":"2022-07-19","cited_by_count":62,"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":"2112.01551","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","created":"2021-12-02","cited_by_count":52,"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":"2107.12514","title":"Language Grounding with 3D Objects","created":"2021-07-26","cited_by_count":43,"area":null},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34,"area":null},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2212.06250","title":"ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes","created":"2022-12-12","cited_by_count":32,"area":null},{"id":"2305.01921","title":"DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion","created":"2023-05-03","cited_by_count":32,"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":"2104.05857","title":"From partners to populations: A hierarchical Bayesian account of coordination and convention","created":"2021-04-12","cited_by_count":27,"area":null},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27,"area":null},{"id":"2303.10406","title":"3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process","created":"2023-03-18","cited_by_count":25,"area":null},{"id":"2412.01801","title":"SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2210.01946","title":"Affection: Learning Affective Explanations for Real-World Visual Data","created":"2022-10-04","cited_by_count":19,"area":null},{"id":"2108.05863","title":"Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2201.07366","title":"TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval","created":"2022-01-19","cited_by_count":18,"area":null},{"id":"2112.11691","title":"Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation","created":"2021-12-22","cited_by_count":17,"area":null},{"id":"2207.01821","title":"Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2305.12815","title":"Investigating Agency of LLMs in Human-AI Collaboration Tasks","created":"2023-05-22","cited_by_count":15,"area":null},{"id":"2107.01872","title":"Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2210.11795","title":"PoseScript: Linking 3D Human Poses and Natural Language","created":"2022-10-21","cited_by_count":14,"area":null},{"id":"2405.09431","title":"A Survey On Text-to-3D Contents Generation In The Wild","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2403.13289","title":"Text-to-3D Shape Generation","created":"2024-03-20","cited_by_count":13,"area":null},{"id":"2403.18241","title":"NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation","created":"2024-03-27","cited_by_count":13,"area":null},{"id":"2104.14118","title":"REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter","created":"2021-04-29","cited_by_count":11,"area":null},{"id":"2205.09710","title":"Voxel-informed Language Grounding","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2212.05011","title":"LADIS: Language Disentanglement for 3D Shape Editing","created":"2022-12-09","cited_by_count":10,"area":null},{"id":"2203.16168","title":"FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing","created":"2022-03-30","cited_by_count":9,"area":null},{"id":"2212.12952","title":"Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program","created":"2022-12-25","cited_by_count":6,"area":null},{"id":"2312.06116","title":"Stellar: Systematic Evaluation of Human-Centric Personalized Text-to-Image Methods","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2309.07917","title":"Looking at words and points with attention: a benchmark for text-to-shape coherence","created":"2023-09-14","cited_by_count":3,"area":null},{"id":"2311.06694","title":"Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding","created":"2023-11-12","cited_by_count":3,"area":null},{"id":"2402.12923","title":"Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2407.02846","title":"Multi-Task Domain Adaptation for Language Grounding with 3D Objects","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2302.10282","title":"Paparazzi: A Deep Dive into the Capabilities of Language and Vision Models for Grounding Viewpoint Descriptions","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2308.02000","title":"Bridging Neural and Symbolic Representations with Transitional Dictionary Learning","created":"2023-08-03","cited_by_count":1,"area":null},{"id":"2309.03100","title":"FArMARe: a Furniture-Aware Multi-task methodology for Recommending Apartments based on the user interests","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2403.19386","title":"PointCloud-Text Matching: Benchmark Datasets and a Baseline","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2505.06030","title":"Why Are You Wrong? Counterfactual Explanations for Language Grounding with 3D Objects","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2510.14965","title":"ChangingGrounding: 3D Visual Grounding in Changing Scenes","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2411.02858","title":"OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing","created":"2024-11-05","cited_by_count":0,"area":null}],"next_cursor":null}