{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"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":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"2007.11571","title":"Neural Sparse Voxel Fields","created":"2020-07-22","cited_by_count":959},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2107.02791","title":"Depth-supervised NeRF: Fewer Views and Faster Training for Free","created":"2021-07-06","cited_by_count":735},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1711.07566","title":"Neural 3D Mesh Renderer","created":"2017-11-20","cited_by_count":437},{"id":"1812.01024","title":"DeepVoxels: Learning Persistent 3D Feature Embeddings","created":"2018-12-03","cited_by_count":405},{"id":"1808.00671","title":"PCN: Point Completion Network","created":"2018-08-02","cited_by_count":384},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"1905.10711","title":"DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction","created":"2019-05-26","cited_by_count":333},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"2108.08839","title":"PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers","created":"2021-08-19","cited_by_count":286},{"id":"1908.01210","title":"Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer","created":"2019-08-03","cited_by_count":221},{"id":"1804.04610","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","created":"2018-04-12","cited_by_count":218},{"id":"1911.11130","title":"Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild","created":"2019-11-25","cited_by_count":180},{"id":"1603.08637","title":"Learning a Predictable and Generative Vector Representation for Objects","created":"2016-03-29","cited_by_count":173},{"id":"1901.11153","title":"Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images","created":"2019-01-31","cited_by_count":164},{"id":"2003.00410","title":"PF-Net: Point Fractal Network for 3D Point Cloud Completion","created":"2020-03-01","cited_by_count":146},{"id":"1711.03129","title":"MarrNet: 3D Shape Reconstruction via 2.5D Sketches","created":"2017-11-08","cited_by_count":108},{"id":"1612.00814","title":"Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision","created":"2016-12-01","cited_by_count":106},{"id":"2201.10326","title":"ShapeFormer: Transformer-based Shape Completion via Sparse Representation","created":"2022-01-25","cited_by_count":106},{"id":"1908.01491","title":"Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation","created":"2019-08-05","cited_by_count":103},{"id":"2004.00614","title":"Articulation-aware Canonical Surface Mapping","created":"2020-04-01","cited_by_count":81},{"id":"2103.16552","title":"Unsupervised Learning of 3D Object Categories from Videos in the Wild","created":"2021-03-30","cited_by_count":67},{"id":"1909.02533","title":"C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion","created":"2019-09-05","cited_by_count":61},{"id":"2103.12957","title":"Multi-view 3D Reconstruction with Transformer","created":"2021-03-24","cited_by_count":52},{"id":"2212.04386","title":"Multi-View Mesh Reconstruction with Neural Deferred Shading","created":"2022-12-08","cited_by_count":44},{"id":"2101.02697","title":"PVA: Pixel-aligned Volumetric Avatars","created":"2021-01-07","cited_by_count":40},{"id":"1901.05567","title":"Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction","created":"2019-01-17","cited_by_count":28},{"id":"1909.01205","title":"Few-Shot Generalization for Single-Image 3D Reconstruction via Priors","created":"2019-09-03","cited_by_count":25},{"id":"2204.10916","title":"Revealing Occlusions with 4D Neural Fields","created":"2022-04-22","cited_by_count":17},{"id":"1304.3111","title":"Estimating Uncertain Spatial Relationships in Robotics","created":"2013-03-27","cited_by_count":14},{"id":"2112.04481","title":"What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction","created":"2021-12-08","cited_by_count":7}],"next_cursor":null}