{"list":"other","total":87,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1801.09847","title":"Open3D: A Modern Library for 3D Data Processing","created":"2018-01-30","cited_by_count":721},{"id":"2304.06706","title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields","created":"2023-04-13","cited_by_count":671},{"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":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2106.11810","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","created":"2021-06-22","cited_by_count":493},{"id":"2203.11496","title":"TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers","created":"2022-03-22","cited_by_count":466},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"1907.03670","title":"From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network","created":"2019-07-08","cited_by_count":368},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2406.15349","title":"NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking","created":"2024-06-21","cited_by_count":354},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2304.14365","title":"Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving","created":"2023-04-27","cited_by_count":332},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2311.17918","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","created":"2023-11-29","cited_by_count":319},{"id":"2303.09551","title":"SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving","created":"2023-03-16","cited_by_count":316},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"2311.16038","title":"OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving","created":"2023-11-27","cited_by_count":233},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224},{"id":"2303.03991","title":"OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception","created":"2023-03-07","cited_by_count":221},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"id":"2403.06845","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","created":"2024-03-11","cited_by_count":191},{"id":"2008.10559","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","created":"2020-08-24","cited_by_count":188},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2307.01492","title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","created":"2023-07-04","cited_by_count":165},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142},{"id":"2209.15397","title":"KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way","created":"2022-09-30","cited_by_count":132},{"id":"2002.09147","title":"SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances","created":"2020-02-21","cited_by_count":123},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"2410.13571","title":"DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation","created":"2024-10-17","cited_by_count":123},{"id":"1810.10863","title":"GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks","created":"2018-10-25","cited_by_count":107},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"id":"2305.19590","title":"Neural Kernel Surface Reconstruction","created":"2023-05-31","cited_by_count":104},{"id":"2301.04634","title":"Street-View Image Generation from a Bird's-Eye View Layout","created":"2023-01-11","cited_by_count":102},{"id":"2308.01661","title":"BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout","created":"2023-08-03","cited_by_count":102},{"id":"2209.03954","title":"Learning to Generate Realistic LiDAR Point Clouds","created":"2022-09-08","cited_by_count":93},{"id":"2312.02934","title":"WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation","created":"2023-12-05","cited_by_count":93},{"id":"2411.13807","title":"MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control","created":"2024-11-21","cited_by_count":92},{"id":"2412.12507","title":"3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting","created":"2024-12-17","cited_by_count":88},{"id":"2409.03272","title":"OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving","created":"2024-09-05","cited_by_count":83},{"id":"2301.05221","title":"Open-vocabulary Object Segmentation with Diffusion Models","created":"2023-01-12","cited_by_count":82},{"id":"2311.01448","title":"UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation","created":"2023-11-02","cited_by_count":78},{"id":"2405.20337","title":"OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving","created":"2024-05-30","cited_by_count":78},{"id":"2203.15118","title":"LiDAR Snowfall Simulation for Robust 3D Object Detection","created":"2022-03-28","cited_by_count":73},{"id":"2404.00815","title":"Towards Realistic Scene Generation with LiDAR Diffusion Models","created":"2024-03-31","cited_by_count":69},{"id":"2408.14197","title":"Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving","created":"2024-08-26","cited_by_count":69},{"id":"2404.02903","title":"LidarDM: Generative LiDAR Simulation in a Generated World","created":"2024-04-03","cited_by_count":54},{"id":"2403.07773","title":"SemCity: Semantic Scene Generation with Triplane Diffusion","created":"2024-03-12","cited_by_count":53},{"id":"2304.14811","title":"NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields","created":"2023-04-28","cited_by_count":44},{"id":"2311.12085","title":"Pyramid Diffusion for Fine 3D Large Scene Generation","created":"2023-11-20","cited_by_count":44},{"id":"2410.18084","title":"DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes","created":"2024-10-23","cited_by_count":38},{"id":"2501.00601","title":"DreamDrive: Generative 4D Scene Modeling from Street View Images","created":"2024-12-31","cited_by_count":35},{"id":"2510.18313","title":"OmniNWM: Omniscient Driving Navigation World Models","created":"2025-10-21","cited_by_count":33},{"id":"2403.13304","title":"DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception","created":"2024-03-20","cited_by_count":32},{"id":"2407.02077","title":"Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion","created":"2024-07-02","cited_by_count":32},{"id":"1907.04758","title":"SynthCity: A large scale synthetic point cloud","created":"2019-07-10","cited_by_count":26},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24},{"id":"2007.05490","title":"Camera-Lidar Integration: Probabilistic sensor fusion for semantic mapping","created":"2020-07-09","cited_by_count":22},{"id":"2303.13959","title":"Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion","created":"2023-03-24","cited_by_count":22},{"id":"2412.05280","title":"Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model","created":"2024-12-06","cited_by_count":18},{"id":"2501.08983","title":"Compositional Generative Model of Unbounded 4D Cities","created":"2025-01-15","cited_by_count":17},{"id":"2506.03079","title":"ORV: 4D Occupancy-centric Robot Video Generation","created":"2025-06-03","cited_by_count":17},{"id":"2407.06250","title":"FairDiff: Fair Segmentation with Point-Image Diffusion","created":"2024-07-08","cited_by_count":15},{"id":"2306.12681","title":"One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception","created":"2023-06-22","cited_by_count":13},{"id":"2501.13971","title":"GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting","created":"2025-01-22","cited_by_count":13},{"id":"2412.11183","title":"OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation","created":"2024-12-15","cited_by_count":10},{"id":"2412.08243","title":"Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction","created":"2024-12-11","cited_by_count":8}],"next_cursor":null}