{"list":"other","total":188,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"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":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"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":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2312.00109","title":"Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering","created":"2023-11-30","cited_by_count":695},{"id":"2304.06706","title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields","created":"2023-04-13","cited_by_count":671},{"id":"2311.16493","title":"Mip-Splatting: Alias-free 3D Gaussian Splatting","created":"2023-11-27","cited_by_count":667},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"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":"2201.08845","title":"Point-NeRF: Point-based Neural Radiance Fields","created":"2022-01-21","cited_by_count":503},{"id":"2111.04276","title":"Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis","created":"2021-11-08","cited_by_count":460},{"id":"2311.17245","title":"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS","created":"2023-11-28","cited_by_count":436},{"id":"2112.10703","title":"Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs","created":"2021-12-20","cited_by_count":398},{"id":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","cited_by_count":364},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2312.07920","title":"DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes","created":"2023-12-13","cited_by_count":360},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2011.10379","title":"Neural Scene Graphs for Dynamic Scenes","created":"2020-11-20","cited_by_count":298},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2111.14643","title":"Urban Radiance Fields","created":"2021-11-29","cited_by_count":263},{"id":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"1801.01973","title":"A Note on the Inception Score","created":"2018-01-06","cited_by_count":226},{"id":"2311.16473","title":"GS-IR: 3D Gaussian Splatting for Inverse Rendering","created":"2023-11-26","cited_by_count":224},{"id":"2401.01339","title":"Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting","created":"2024-01-02","cited_by_count":221},{"id":"2311.02077","title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","created":"2023-11-03","cited_by_count":217},{"id":"2402.17427","title":"VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction","created":"2024-02-27","cited_by_count":209},{"id":"2008.03824","title":"Neural Reflectance Fields for Appearance Acquisition","created":"2020-08-09","cited_by_count":196},{"id":"2312.09228","title":"3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting","created":"2023-12-14","cited_by_count":195},{"id":"2404.01133","title":"CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians","created":"2024-04-01","cited_by_count":192},{"id":"2112.12610","title":"PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving","created":"2021-12-23","cited_by_count":190},{"id":"2309.16553","title":"MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond","created":"2023-09-28","cited_by_count":185},{"id":"2005.10821","title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","created":"2020-05-21","cited_by_count":183},{"id":"2206.08929","title":"TAVA: Template-free Animatable Volumetric Actors","created":"2022-06-17","cited_by_count":172},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"2307.15058","title":"MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving","created":"2023-07-27","cited_by_count":170},{"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},{"id":"2408.16760","title":"OmniRe: Omni Urban Scene Reconstruction","created":"2024-08-29","cited_by_count":161},{"id":"1707.05776","title":"Optimizing the Latent Space of Generative Networks","created":"2017-07-18","cited_by_count":157},{"id":"2407.08447","title":"WildGaussians: 3D Gaussian Splatting in the Wild","created":"2024-07-11","cited_by_count":152},{"id":"2303.14536","title":"SUDS: Scalable Urban Dynamic Scenes","created":"2023-03-25","cited_by_count":151},{"id":"2311.15260","title":"NeuRAD: Neural Rendering for Autonomous Driving","created":"2023-11-26","cited_by_count":150},{"id":"2311.18561","title":"Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering","created":"2023-11-30","cited_by_count":143},{"id":"2207.11911","title":"NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing","created":"2022-07-25","cited_by_count":142},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142},{"id":"2212.10550","title":"InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds","created":"2022-12-20","cited_by_count":138},{"id":"2110.07604","title":"NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild","created":"2021-10-14","cited_by_count":136},{"id":"2302.11566","title":"Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition","created":"2023-02-22","cited_by_count":134},{"id":"2212.03293","title":"Diffusion-SDF: Text-to-Shape via Voxelized Diffusion","created":"2022-12-06","cited_by_count":128},{"id":"2306.04988","title":"StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views","created":"2023-06-08","cited_by_count":120},{"id":"2107.04286","title":"Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset","created":"2021-07-09","cited_by_count":118},{"id":"2303.15951","title":"F$^{2}$-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories","created":"2023-03-28","cited_by_count":118},{"id":"2303.00749","title":"S-NeRF: Neural Radiance Fields for Street Views","created":"2023-03-01","cited_by_count":116},{"id":"2306.10013","title":"PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation","created":"2023-06-16","cited_by_count":115},{"id":"2112.05140","title":"NeRF for Outdoor Scene Relighting","created":"2021-12-09","cited_by_count":114},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"id":"2405.20323","title":"$\\textit{S}^3$Gaussian: Self-Supervised Street Gaussians for Autonomous Driving","created":"2024-05-30","cited_by_count":105},{"id":"2302.00833","title":"RobustNeRF: Ignoring Distractors with Robust Losses","created":"2023-02-02","cited_by_count":101},{"id":"2404.09502","title":"SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction","created":"2024-04-15","cited_by_count":96},{"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":"2206.12055","title":"SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation","created":"2022-06-24","cited_by_count":92},{"id":"2304.03266","title":"Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenes","created":"2023-04-06","cited_by_count":90},{"id":"2405.18715","title":"NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild","created":"2024-05-29","cited_by_count":85},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83},{"id":"2404.00409","title":"3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting","created":"2024-03-30","cited_by_count":79},{"id":"2502.13144","title":"RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning","created":"2025-02-18","cited_by_count":79}],"next_cursor":"100"}