{"list":"other","total":153,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2112.05131","title":"Plenoxels: Radiance Fields without Neural Networks","created":"2021-12-09","cited_by_count":1613},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"id":"2106.12052","title":"Volume Rendering of Neural Implicit Surfaces","created":"2021-06-22","cited_by_count":996},{"id":"2111.11215","title":"Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction","created":"2021-11-22","cited_by_count":964},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"2007.02442","title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","created":"2020-07-05","cited_by_count":689},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"1905.00889","title":"Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines","created":"2019-05-02","cited_by_count":672},{"id":"1703.00848","title":"Unsupervised Image-to-Image Translation Networks","created":"2017-03-02","cited_by_count":603},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2302.04264","title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development","created":"2023-02-08","cited_by_count":600},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540},{"id":"2302.08113","title":"MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation","created":"2023-02-16","cited_by_count":536},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2012.03927","title":"NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis","created":"2020-12-07","cited_by_count":496},{"id":"2310.10642","title":"Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting","created":"2023-10-16","cited_by_count":476},{"id":"1711.07566","title":"Neural 3D Mesh Renderer","created":"2017-11-20","cited_by_count":437},{"id":"2306.17843","title":"Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors","created":"2023-06-30","cited_by_count":397},{"id":"2311.12198","title":"PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics","created":"2023-11-20","cited_by_count":377},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365},{"id":"1907.03739","title":"Point-Voxel CNN for Efficient 3D Deep Learning","created":"2019-07-08","cited_by_count":343},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"2311.14521","title":"GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting","created":"2023-11-24","cited_by_count":335},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334},{"id":"2208.00277","title":"MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures","created":"2022-07-30","cited_by_count":311},{"id":"2302.01721","title":"TEXTure: Text-Guided Texturing of 3D Shapes","created":"2023-02-03","cited_by_count":304},{"id":"1808.00948","title":"Diverse Image-to-Image Translation via Disentangled Representations","created":"2018-08-02","cited_by_count":296},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291},{"id":"2004.03805","title":"State of the Art on Neural Rendering","created":"2020-04-08","cited_by_count":278},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"1904.12356","title":"Deferred Neural Rendering: Image Synthesis using Neural Textures","created":"2019-04-28","cited_by_count":253},{"id":"2303.11396","title":"Text2Tex: Text-driven Texture Synthesis via Diffusion Models","created":"2023-03-20","cited_by_count":235},{"id":"2008.05511","title":"Free View Synthesis","created":"2020-08-12","cited_by_count":231},{"id":"2112.05504","title":"BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering","created":"2021-12-10","cited_by_count":229},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203},{"id":"1705.04058","title":"Neural Style Transfer: A Review","created":"2017-05-11","cited_by_count":199},{"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":"1605.04797","title":"Thingi10K: A Dataset of 10,000 3D-Printing Models","created":"2016-05-16","cited_by_count":183},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183},{"id":"2108.03647","title":"AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer","created":"2021-08-08","cited_by_count":178},{"id":"1703.07511","title":"Deep Photo Style Transfer","created":"2017-03-22","cited_by_count":168},{"id":"2002.08988","title":"BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images","created":"2020-02-20","cited_by_count":166},{"id":"2108.00946","title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","created":"2021-08-02","cited_by_count":164},{"id":"2306.13455","title":"DreamEditor: Text-Driven 3D Scene Editing with Neural Fields","created":"2023-06-23","cited_by_count":155},{"id":"2210.15947","title":"NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields","created":"2022-10-28","cited_by_count":152},{"id":"2303.14536","title":"SUDS: Scalable Urban Dynamic Scenes","created":"2023-03-25","cited_by_count":151},{"id":"2206.06360","title":"ARF: Artistic Radiance Fields","created":"2022-06-13","cited_by_count":147},{"id":"2205.12183","title":"StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning","created":"2022-05-24","cited_by_count":140},{"id":"2310.02596","title":"SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D","created":"2023-10-04","cited_by_count":134},{"id":"2209.08725","title":"Neural Wavelet-domain Diffusion for 3D Shape Generation","created":"2022-09-19","cited_by_count":132},{"id":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127},{"id":"2212.08070","title":"NeRF-Art: Text-Driven Neural Radiance Fields Stylization","created":"2022-12-15","cited_by_count":126},{"id":"2304.07090","title":"Delta Denoising Score","created":"2023-04-14","cited_by_count":121}],"next_cursor":"100"}