{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2011.12100","title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","created":"2020-11-24","cited_by_count":785},{"id":"2012.00926","title":"pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis","created":"2020-12-02","cited_by_count":708},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"1607.08128","title":"Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image","created":"2016-07-27","cited_by_count":695},{"id":"2007.02442","title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","created":"2020-07-05","cited_by_count":689},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2004.00452","title":"PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization","created":"2020-04-01","cited_by_count":521},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"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":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2011.03277","title":"Modular Primitives for High-Performance Differentiable Rendering","created":"2020-11-06","cited_by_count":441},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"1812.01601","title":"Learning 3D Human Dynamics from Video","created":"2018-12-04","cited_by_count":316},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"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":"2003.06473","title":"Self-supervised Single-view 3D Reconstruction via Semantic Consistency","created":"2020-03-13","cited_by_count":127},{"id":"1904.11111","title":"Learning the Depths of Moving People by Watching Frozen People","created":"2019-04-25","cited_by_count":120},{"id":"2105.02976","title":"LASR: Learning Articulated Shape Reconstruction from a Monocular Video","created":"2021-05-06","cited_by_count":116},{"id":"2311.14603","title":"Animate124: Animating One Image to 4D Dynamic Scene","created":"2023-11-24","cited_by_count":115},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"2311.16854","title":"A Unified Approach for Text- and Image-guided 4D Scene Generation","created":"2023-11-28","cited_by_count":82},{"id":"2004.00614","title":"Articulation-aware Canonical Surface Mapping","created":"2020-04-01","cited_by_count":81},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2207.03434","title":"LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery","created":"2022-07-07","cited_by_count":66},{"id":"1907.10043","title":"Canonical Surface Mapping via Geometric Cycle Consistency","created":"2019-07-23","cited_by_count":63},{"id":"2107.10844","title":"DOVE: Learning Deformable 3D Objects by Watching Videos","created":"2021-07-22","cited_by_count":61},{"id":"1904.01326","title":"HoloGAN: Unsupervised learning of 3D representations from natural images","created":"2019-04-02","cited_by_count":59},{"id":"2206.05683","title":"APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking","created":"2022-06-12","cited_by_count":56},{"id":"2203.16875","title":"MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images","created":"2022-03-31","cited_by_count":53},{"id":"1908.04781","title":"Predicting 3D Human Dynamics from Video","created":"2019-08-13","cited_by_count":51},{"id":"2012.03196","title":"Online Adaptation for Consistent Mesh Reconstruction in the Wild","created":"2020-12-06","cited_by_count":51},{"id":"2305.06351","title":"Reconstructing Animatable Categories from Videos","created":"2023-05-10","cited_by_count":47},{"id":"1804.10652","title":"Human Motion Modeling using DVGANs","created":"2018-04-27","cited_by_count":45},{"id":"2304.10535","title":"Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion","created":"2023-04-20","cited_by_count":38},{"id":"2206.08361","title":"Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields","created":"2022-06-16","cited_by_count":37},{"id":"2310.14729","title":"MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion","created":"2023-10-23","cited_by_count":37},{"id":"2211.03568","title":"CASA: Category-agnostic Skeletal Animal Reconstruction","created":"2022-11-04","cited_by_count":35},{"id":"2212.11042","title":"Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble","created":"2022-12-21","cited_by_count":31},{"id":"2205.06267","title":"Topologically-Aware Deformation Fields for Single-View 3D Reconstruction","created":"2022-05-12","cited_by_count":29},{"id":"2104.03954","title":"De-rendering the World's Revolutionary Artefacts","created":"2021-04-08","cited_by_count":28},{"id":"2103.06747","title":"ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References","created":"2021-03-11","cited_by_count":26},{"id":"2112.05121","title":"Self-Supervised Keypoint Discovery in Behavioral Videos","created":"2021-12-09","cited_by_count":23},{"id":"2306.04619","title":"ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections","created":"2023-06-07","cited_by_count":22},{"id":"2106.05662","title":"To The Point: Correspondence-driven monocular 3D category reconstruction","created":"2021-06-10","cited_by_count":21},{"id":"2105.02431","title":"Inverting Generative Adversarial Renderer for Face Reconstruction","created":"2021-05-06","cited_by_count":17},{"id":"2212.07401","title":"BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos","created":"2022-12-14","cited_by_count":10},{"id":"2304.14396","title":"Learning Articulated Shape with Keypoint Pseudo-labels from Web Images","created":"2023-04-27","cited_by_count":5}],"next_cursor":null}