{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245},{"id":"1904.06447","title":"Learning Shape Templates with Structured Implicit Functions","created":"2019-04-12","cited_by_count":242},{"id":"2110.03675","title":"ATISS: Autoregressive Transformers for Indoor Scene Synthesis","created":"2021-10-07","cited_by_count":200},{"id":"2312.03806","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","created":"2023-12-06","cited_by_count":189},{"id":"1612.00404","title":"Learning Shape Abstractions by Assembling Volumetric Primitives","created":"2016-12-01","cited_by_count":181},{"id":"1909.05736","title":"CvxNet: Learnable Convex Decomposition","created":"2019-09-12","cited_by_count":174},{"id":"2303.14207","title":"DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis","created":"2023-03-24","cited_by_count":166},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2302.01133","title":"SceneScape: Text-Driven Consistent Scene Generation","created":"2023-02-02","cited_by_count":160},{"id":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158},{"id":"1904.09970","title":"Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids","created":"2019-04-22","cited_by_count":124},{"id":"2305.11588","title":"Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields","created":"2023-05-19","cited_by_count":123},{"id":"2402.04717","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","created":"2024-02-07","cited_by_count":117},{"id":"2404.07199","title":"RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion","created":"2024-04-10","cited_by_count":109},{"id":"1811.12463","title":"Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models","created":"2018-11-29","cited_by_count":106},{"id":"2103.10429","title":"Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks","created":"2021-03-18","cited_by_count":103},{"id":"2303.12218","title":"Compositional 3D Scene Generation using Locally Conditioned Diffusion","created":"2023-03-21","cited_by_count":101},{"id":"2204.13683","title":"KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients","created":"2022-04-28","cited_by_count":96},{"id":"2101.06541","title":"SceneGen: Learning to Generate Realistic Traffic Scenes","created":"2021-01-16","cited_by_count":84},{"id":"2108.08841","title":"Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs","created":"2021-08-19","cited_by_count":84},{"id":"2401.17053","title":"BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation","created":"2024-01-30","cited_by_count":83},{"id":"2004.02869","title":"DualSDF: Semantic Shape Manipulation using a Two-Level Representation","created":"2020-04-06","cited_by_count":82},{"id":"1708.01648","title":"3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks","created":"2017-08-04","cited_by_count":77},{"id":"2301.09629","title":"LEGO-Net: Learning Regular Rearrangements of Objects in Rooms","created":"2023-01-23","cited_by_count":76},{"id":"2309.00610","title":"CityDreamer: Compositional Generative Model of Unbounded 3D Cities","created":"2023-09-01","cited_by_count":76},{"id":"2004.01176","title":"Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image","created":"2020-04-02","cited_by_count":72},{"id":"2301.09637","title":"InfiniCity: Infinite-Scale City Synthesis","created":"2023-01-23","cited_by_count":68},{"id":"2405.00915","title":"EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion","created":"2024-05-02","cited_by_count":67},{"id":"2303.12236","title":"SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation","created":"2023-03-21","cited_by_count":66},{"id":"2212.11984","title":"DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis","created":"2022-12-22","cited_by_count":61},{"id":"2303.12074","title":"CC3D: Layout-Conditioned Generation of Compositional 3D Scenes","created":"2023-03-21","cited_by_count":58},{"id":"1804.05469","title":"Im2Struct: Recovering 3D Shape Structure from a Single RGB Image","created":"2018-04-16","cited_by_count":55},{"id":"2409.08215","title":"LT3SD: Latent Trees for 3D Scene Diffusion","created":"2024-09-12","cited_by_count":55},{"id":"2305.11337","title":"RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture","created":"2023-05-18","cited_by_count":53},{"id":"2403.07773","title":"SemCity: Semantic Scene Generation with Triplane Diffusion","created":"2024-03-12","cited_by_count":53},{"id":"2408.13252","title":"LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation","created":"2024-08-23","cited_by_count":53},{"id":"2007.11744","title":"End-to-End Optimization of Scene Layout","created":"2020-07-23","cited_by_count":52},{"id":"2412.12129","title":"SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout","created":"2024-12-05","cited_by_count":48},{"id":"2311.12085","title":"Pyramid Diffusion for Fine 3D Large Scene Generation","created":"2023-11-20","cited_by_count":44},{"id":"2406.06526","title":"Generative Gaussian Splatting for Unbounded 3D City Generation","created":"2024-06-10","cited_by_count":44},{"id":"2312.09242","title":"Text2Immersion: Generative Immersive Scene with 3D Gaussians","created":"2023-12-14","cited_by_count":43},{"id":"2410.09049","title":"SceneCraft: Layout-Guided 3D Scene Generation","created":"2024-10-11","cited_by_count":41},{"id":"2106.14880","title":"HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps","created":"2021-06-28","cited_by_count":40},{"id":"2203.07060","title":"MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environments","created":"2022-03-14","cited_by_count":40},{"id":"2412.21117","title":"Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation","created":"2024-12-30","cited_by_count":34},{"id":"2503.22496","title":"Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments","created":"2025-03-28","cited_by_count":28},{"id":"2309.14685","title":"DriveSceneGen: Generating Diverse and Realistic Driving Scenarios from Scratch","created":"2023-09-26","cited_by_count":27},{"id":"2403.17933","title":"SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic","created":"2024-03-26","cited_by_count":27},{"id":"2303.14167","title":"UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields","created":"2023-03-24","cited_by_count":26},{"id":"2412.01801","title":"SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation","created":"2024-12-02","cited_by_count":24},{"id":"2312.01508","title":"CityGen: Infinite and Controllable City Layout Generation","created":"2023-12-03","cited_by_count":22},{"id":"2404.06780","title":"Urban Architect: Steerable 3D Urban Scene Generation with Layout Prior","created":"2024-04-10","cited_by_count":17},{"id":"2303.13514","title":"SAOR: Single-View Articulated Object Reconstruction","created":"2023-03-23","cited_by_count":16},{"id":"2501.02519","title":"Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors","created":"2025-01-05","cited_by_count":13},{"id":"2503.16611","title":"A Recipe for Generating 3D Worlds From a Single Image","created":"2025-03-20","cited_by_count":13},{"id":"2504.10485","title":"Decoupled Diffusion Sparks Adaptive Scene Generation","created":"2025-04-14","cited_by_count":12},{"id":"2504.00387","title":"Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration","created":"2025-04-01","cited_by_count":11},{"id":"2307.04246","title":"Convex Decomposition of Indoor Scenes","created":"2023-07-09","cited_by_count":7},{"id":"2307.03847","title":"Blocks2World: Controlling Realistic Scenes with Editable Primitives","created":"2023-07-07","cited_by_count":4},{"id":"2411.12290","title":"SSEditor: Controllable Mask-to-Scene Generation with Diffusion Model","created":"2024-11-19","cited_by_count":2}],"next_cursor":null}