{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"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":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"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":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2106.12052","title":"Volume Rendering of Neural Implicit Surfaces","created":"2021-06-22","cited_by_count":996},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2104.10078","title":"UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction","created":"2021-04-20","cited_by_count":646},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2206.00665","title":"MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction","created":"2022-06-01","cited_by_count":470},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2104.04532","title":"Neural RGB-D Surface Reconstruction","created":"2021-04-09","cited_by_count":313},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237},{"id":"1804.04610","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","created":"2018-04-12","cited_by_count":218},{"id":"2106.03452","title":"Shape As Points: A Differentiable Poisson Solver","created":"2021-06-07","cited_by_count":187},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"id":"2206.13597","title":"NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors","created":"2022-06-27","cited_by_count":125},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2111.02444","title":"Panoptic 3D Scene Reconstruction From a Single RGB Image","created":"2021-11-03","cited_by_count":70},{"id":"2410.14189","title":"Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set","created":"2024-10-18","cited_by_count":49},{"id":"2210.02757","title":"CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization","created":"2022-10-06","cited_by_count":47},{"id":"2203.15190","title":"3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow","created":"2022-03-29","cited_by_count":45},{"id":"2305.11601","title":"Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment","created":"2023-05-19","cited_by_count":39},{"id":"2208.06821","title":"Fast Learning Radiance Fields by Shooting Much Fewer Rays","created":"2022-08-14","cited_by_count":38},{"id":"2211.16869","title":"NeAF: Learning Neural Angle Fields for Point Normal Estimation","created":"2022-11-30","cited_by_count":38},{"id":"2312.04060","title":"Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching","created":"2023-12-07","cited_by_count":37},{"id":"2312.13977","title":"NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views","created":"2023-12-21","cited_by_count":37},{"id":"2308.11441","title":"Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection","created":"2023-08-22","cited_by_count":36},{"id":"2311.17971","title":"GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation","created":"2023-11-29","cited_by_count":30},{"id":"2108.03746","title":"Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching","created":"2021-08-08","cited_by_count":26},{"id":"2211.14157","title":"Learning 3D Scene Priors with 2D Supervision","created":"2022-11-25","cited_by_count":24},{"id":"2404.06851","title":"UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion","created":"2024-04-10","cited_by_count":23},{"id":"2306.00965","title":"BUOL: A Bottom-Up Framework with Occupancy-aware Lifting for Panoptic 3D Scene Reconstruction From A Single Image","created":"2023-06-01","cited_by_count":20},{"id":"2312.15133","title":"Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling","created":"2023-12-23","cited_by_count":19},{"id":"2203.14084","title":"3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds","created":"2022-03-26","cited_by_count":18},{"id":"2407.16396","title":"VRP-UDF: Towards Unbiased Learning of Unsigned Distance Functions from Multi-view Images with Volume Rendering Priors","created":"2024-07-23","cited_by_count":17},{"id":"2407.14225","title":"Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping","created":"2024-07-04","cited_by_count":15}],"next_cursor":null}