{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"2202.09778","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","created":"2022-02-20","cited_by_count":700},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2205.13790","title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","created":"2022-05-27","cited_by_count":336},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252},{"id":"1708.01642","title":"Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection","created":"2017-08-04","cited_by_count":209},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2311.15260","title":"NeuRAD: Neural Rendering for Autonomous Driving","created":"2023-11-26","cited_by_count":150},{"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":"2402.05746","title":"Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents","created":"2024-02-08","cited_by_count":91},{"id":"1803.01837","title":"ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing","created":"2018-03-05","cited_by_count":90},{"id":"2311.01448","title":"UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation","created":"2023-11-02","cited_by_count":78},{"id":"2101.06543","title":"GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving","created":"2021-01-16","cited_by_count":75},{"id":"2310.07771","title":"DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model","created":"2023-10-11","cited_by_count":75},{"id":"2307.11073","title":"OBJECT 3DIT: Language-guided 3D-aware Image Editing","created":"2023-07-20","cited_by_count":63},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53},{"id":"1702.07836","title":"Synthesizing Training Data for Object Detection in Indoor Scenes","created":"2017-02-25","cited_by_count":48},{"id":"2401.01702","title":"Image Sculpting: Precise Object Editing with 3D Geometry Control","created":"2024-01-02","cited_by_count":45},{"id":"2403.19438","title":"SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control","created":"2024-03-28","cited_by_count":32},{"id":"2311.01447","title":"CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation","created":"2023-11-02","cited_by_count":26},{"id":"2310.19784","title":"CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models","created":"2023-10-30","cited_by_count":25},{"id":"2409.05463","title":"DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation","created":"2024-09-09","cited_by_count":22},{"id":"2104.05858","title":"Exploring Geometric Consistency for Monocular 3D Object Detection","created":"2021-04-12","cited_by_count":17},{"id":"2304.03526","title":"Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field","created":"2023-04-07","cited_by_count":15},{"id":"2402.04504","title":"Text2Street: Controllable Text-to-image Generation for Street Views","created":"2024-02-07","cited_by_count":13},{"id":"2402.16392","title":"Placing Objects in Context via Inpainting for Out-of-distribution Segmentation","created":"2024-02-26","cited_by_count":12},{"id":"2406.10722","title":"GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR","created":"2024-06-15","cited_by_count":12},{"id":"2412.14494","title":"Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles","created":"2024-12-19","cited_by_count":10},{"id":"2412.07385","title":"LOGen: Toward Lidar Object Generation by Point Diffusion","created":"2024-12-10","cited_by_count":9},{"id":"2312.14919","title":"Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers","created":"2023-12-22","cited_by_count":8},{"id":"2401.14314","title":"MultiTest: Physical-Aware Object Insertion for Testing Multi-sensor Fusion Perception Systems","created":"2024-01-25","cited_by_count":6},{"id":"2408.07605","title":"Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2024-08-14","cited_by_count":5},{"id":"2312.12419","title":"Scene-Conditional 3D Object Stylization and Composition","created":"2023-12-19","cited_by_count":4},{"id":"2403.11573","title":"Just Add $100 More: Augmenting NeRF-based Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem","created":"2024-03-18","cited_by_count":4}],"next_cursor":null}