{"list":"other","total":59,"rows":[{"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":"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"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":"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":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"1803.04189","title":"Noise2Noise: Learning Image Restoration without Clean Data","created":"2018-03-12","cited_by_count":533},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"2307.12348","title":"ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting","created":"2023-07-23","cited_by_count":365},{"id":"2111.13679","title":"NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images","created":"2021-11-26","cited_by_count":336},{"id":"1904.04717","title":"Label Propagation for Deep Semi-supervised Learning","created":"2019-04-09","cited_by_count":289},{"id":"1906.07316","title":"DeepView: View Synthesis with Learned Gradient Descent","created":"2019-06-18","cited_by_count":253},{"id":"2103.05606","title":"NeX: Real-time View Synthesis with Neural Basis Expansion","created":"2021-03-09","cited_by_count":216},{"id":"1805.09817","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","created":"2018-05-24","cited_by_count":211},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"2206.06360","title":"ARF: Artistic Radiance Fields","created":"2022-06-13","cited_by_count":147},{"id":"2305.14093","title":"Weakly Supervised 3D Open-vocabulary Segmentation","created":"2023-05-23","cited_by_count":135},{"id":"2212.08070","title":"NeRF-Art: Text-Driven Neural Radiance Fields Stylization","created":"2022-12-15","cited_by_count":126},{"id":"2306.09347","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","created":"2023-06-15","cited_by_count":125},{"id":"2207.10662","title":"Generalizable Patch-Based Neural Rendering","created":"2022-07-21","cited_by_count":122},{"id":"2207.13298","title":"Is Attention All That NeRF Needs?","created":"2022-07-27","cited_by_count":113},{"id":"2112.09687","title":"Light Field Neural Rendering","created":"2021-12-17","cited_by_count":108},{"id":"2105.13016","title":"Stylizing 3D Scene via Implicit Representation and HyperNetwork","created":"2021-05-27","cited_by_count":103},{"id":"2205.09542","title":"Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning","created":"2022-05-19","cited_by_count":93},{"id":"2303.10598","title":"StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields","created":"2023-03-19","cited_by_count":79},{"id":"2105.13509","title":"Learning to Stylize Novel Views","created":"2021-05-27","cited_by_count":76},{"id":"2209.08776","title":"NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes","created":"2022-09-19","cited_by_count":71},{"id":"2204.01943","title":"Unified Implicit Neural Stylization","created":"2022-04-05","cited_by_count":67},{"id":"2212.13545","title":"Interactive Segmentation of Radiance Fields","created":"2022-12-27","cited_by_count":60},{"id":"2310.08586","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","created":"2023-10-12","cited_by_count":56},{"id":"2306.03899","title":"Towards Label-free Scene Understanding by Vision Foundation Models","created":"2023-06-06","cited_by_count":54},{"id":"2301.00157","title":"Ponder: Point Cloud Pre-training via Neural Rendering","created":"2022-12-31","cited_by_count":50},{"id":"2303.12786","title":"FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models","created":"2023-03-22","cited_by_count":47},{"id":"2207.04808","title":"CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer","created":"2022-07-11","cited_by_count":46},{"id":"2212.11613","title":"DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders","created":"2022-12-22","cited_by_count":36},{"id":"2303.13014","title":"Semantic Ray: Learning a Generalizable Semantic Field with Cross-Reprojection Attention","created":"2023-03-23","cited_by_count":29},{"id":"2308.11793","title":"Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts","created":"2023-08-22","cited_by_count":27},{"id":"2310.15712","title":"GNeSF: Generalizable Neural Semantic Fields","created":"2023-10-24","cited_by_count":9}],"next_cursor":null}