{"total":120,"rows":[{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803,"area":null},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460,"area":"diffusion"},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287,"area":null},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276,"area":null},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263,"area":null},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250,"area":null},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228,"area":null},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224,"area":null},{"id":"2104.14643","title":"AGORA: Avatars in Geography Optimized for Regression Analysis","created":"2021-04-29","cited_by_count":205,"area":null},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194,"area":null},{"id":"2109.01129","title":"NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo","created":"2021-09-02","cited_by_count":192,"area":null},{"id":"2104.14540","title":"The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth","created":"2021-04-29","cited_by_count":190,"area":null},{"id":"2202.08614","title":"Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time","created":"2022-02-17","cited_by_count":165,"area":null},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161,"area":"diffusion"},{"id":"2210.00379","title":"NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)","created":"2022-10-01","cited_by_count":158,"area":null},{"id":"2108.11944","title":"Probabilistic Modeling for Human Mesh Recovery","created":"2021-08-26","cited_by_count":153,"area":null},{"id":"2104.14786","title":"Editable Free-viewpoint Video Using a Layered Neural Representation","created":"2021-04-30","cited_by_count":148,"area":null},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148,"area":null},{"id":"2110.00620","title":"SPEC: Seeing People in the Wild with an Estimated Camera","created":"2021-10-01","cited_by_count":135,"area":null},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116,"area":null},{"id":"2203.01923","title":"Recovering 3D Human Mesh from Monocular Images: A Survey","created":"2022-03-03","cited_by_count":103,"area":null},{"id":"2309.07906","title":"Generative Image Dynamics","created":"2023-09-14","cited_by_count":94,"area":null},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89,"area":null},{"id":"2304.04452","title":"Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos","created":"2023-04-10","cited_by_count":77,"area":null},{"id":"2205.13775","title":"A Survey on Long-Tailed Visual Recognition","created":"2022-05-27","cited_by_count":75,"area":null},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69,"area":null},{"id":"2107.10844","title":"DOVE: Learning Deformable 3D Objects by Watching Videos","created":"2021-07-22","cited_by_count":61,"area":null},{"id":"2111.15669","title":"360MonoDepth: High-Resolution 360{\\deg} Monocular Depth Estimation","created":"2021-11-30","cited_by_count":60,"area":null},{"id":"2108.01166","title":"Consistent Depth of Moving Objects in Video","created":"2021-08-02","cited_by_count":56,"area":null},{"id":"2104.13918","title":"High-Resolution Optical Flow from 1D Attention and Correlation","created":"2021-04-28","cited_by_count":54,"area":null},{"id":"2211.03660","title":"SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes","created":"2022-11-07","cited_by_count":52,"area":null},{"id":"2109.01068","title":"SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting","created":"2021-09-02","cited_by_count":48,"area":null},{"id":"2203.15174","title":"Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth","created":"2022-03-29","cited_by_count":48,"area":null},{"id":"2208.13241","title":"Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image","created":"2022-08-28","cited_by_count":42,"area":null},{"id":"2204.06107","title":"Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity","created":"2022-04-12","cited_by_count":41,"area":null},{"id":"2403.09623","title":"Score-Guided Diffusion for 3D Human Recovery","created":"2024-03-14","cited_by_count":39,"area":"diffusion"},{"id":"2107.12429","title":"MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments","created":"2021-07-26","cited_by_count":38,"area":null},{"id":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34,"area":null},{"id":"2310.13768","title":"PACE: Human and Camera Motion Estimation from in-the-wild Videos","created":"2023-10-20","cited_by_count":34,"area":null},{"id":"2111.14562","title":"Instance-wise Occlusion and Depth Orders in Natural Scenes","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2206.08365","title":"Virtual Correspondence: Humans as a Cue for Extreme-View Geometry","created":"2022-06-16","cited_by_count":25,"area":null},{"id":"2103.08468","title":"Beyond Image to Depth: Improving Depth Prediction using Echoes","created":"2021-03-15","cited_by_count":24,"area":null},{"id":"2205.02301","title":"BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking","created":"2022-05-04","cited_by_count":24,"area":null},{"id":"2312.01407","title":"VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams","created":"2023-12-03","cited_by_count":22,"area":null},{"id":"2312.13604","title":"Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos","created":"2023-12-21","cited_by_count":21,"area":null},{"id":"2106.10859","title":"Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panorama","created":"2021-06-21","cited_by_count":19,"area":null},{"id":"2301.05175","title":"Scene-Aware 3D Multi-Human Motion Capture from a Single Camera","created":"2023-01-12","cited_by_count":19,"area":null},{"id":"2303.03315","title":"MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision","created":"2023-03-06","cited_by_count":19,"area":null},{"id":"2204.10320","title":"SelfD: Self-Learning Large-Scale Driving Policies From the Web","created":"2022-04-21","cited_by_count":18,"area":"driving"},{"id":"2202.00909","title":"CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving","created":"2022-02-02","cited_by_count":16,"area":null},{"id":"2208.10762","title":"Depth Map Decomposition for Monocular Depth Estimation","created":"2022-08-23","cited_by_count":16,"area":null},{"id":"2208.11251","title":"Learnable human mesh triangulation for 3D human pose and shape estimation","created":"2022-08-24","cited_by_count":16,"area":null},{"id":"2202.08010","title":"360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse Network","created":"2022-02-16","cited_by_count":15,"area":null},{"id":"2204.02509","title":"Depth-Guided Sparse Structure-from-Motion for Movies and TV Shows","created":"2022-04-05","cited_by_count":15,"area":null},{"id":"2205.06255","title":"3D Moments from Near-Duplicate Photos","created":"2022-05-12","cited_by_count":15,"area":null},{"id":"2409.17331","title":"ChatCam: Empowering Camera Control through Conversational AI","created":"2024-09-25","cited_by_count":15,"area":null},{"id":"2106.13217","title":"Exploring Depth Contribution for Camouflaged Object Detection","created":"2021-06-24","cited_by_count":14,"area":null},{"id":"2206.00468","title":"PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation","created":"2022-06-01","cited_by_count":14,"area":null},{"id":"2309.14291","title":"Tiled Multiplane Images for Practical 3D Photography","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2103.03319","title":"Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos","created":"2021-03-04","cited_by_count":12,"area":null},{"id":"2105.12053","title":"Real-time Monocular Depth Estimation with Sparse Supervision on Mobile","created":"2021-05-25","cited_by_count":12,"area":null},{"id":"2202.06088","title":"NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing","created":"2022-02-12","cited_by_count":12,"area":null},{"id":"2207.08951","title":"MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments","created":"2022-07-18","cited_by_count":12,"area":null},{"id":"2304.07435","title":"Temporally Consistent Online Depth Estimation Using Point-Based Fusion","created":"2023-04-15","cited_by_count":12,"area":null},{"id":"2201.05761","title":"A Survey on RGB-D Datasets","created":"2022-01-15","cited_by_count":11,"area":null},{"id":"2512.25075","title":"SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time","created":"2025-12-31","cited_by_count":11,"area":"diffusion"},{"id":"2112.01502","title":"Dimensions of Motion: Monocular Prediction through Flow Subspaces","created":"2021-12-02","cited_by_count":10,"area":null},{"id":"2201.08131","title":"GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding","created":"2022-01-20","cited_by_count":9,"area":null},{"id":"2205.01656","title":"GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mapping","created":"2022-05-03","cited_by_count":8,"area":null},{"id":"2302.10781","title":"Learning 3D Photography Videos via Self-supervised Diffusion on Single Images","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2305.13220","title":"Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids","created":"2023-05-22","cited_by_count":8,"area":null},{"id":"2311.18801","title":"Distributed Global Structure-from-Motion with a Deep Front-End","created":"2023-11-30","cited_by_count":8,"area":null},{"id":"2204.10211","title":"SmartPortraits: Depth Powered Handheld Smartphone Dataset of Human Portraits for State Estimation, Reconstruction and Synthesis","created":"2022-04-21","cited_by_count":7,"area":null},{"id":"2305.12955","title":"Gated Stereo: Joint Depth Estimation from Gated and Wide-Baseline Active Stereo Cues","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2306.08887","title":"SplatFlow: Learning Multi-frame Optical Flow via Splatting","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2506.13697","title":"Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry","created":"2025-06-16","cited_by_count":7,"area":null},{"id":"2112.02416","title":"Gated2Gated: Self-Supervised Depth Estimation from Gated Images","created":"2021-12-04","cited_by_count":6,"area":null},{"id":"2306.02878","title":"Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2503.00746","title":"DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2108.05615","title":"DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes","created":"2021-08-12","cited_by_count":5,"area":null},{"id":"2210.02785","title":"FloatingFusion: Depth from ToF and Image-stabilized Stereo Cameras","created":"2022-10-06","cited_by_count":5,"area":null},{"id":"2304.02797","title":"DeLiRa: Self-Supervised Depth, Light, and Radiance Fields","created":"2023-04-06","cited_by_count":5,"area":null},{"id":"2412.07696","title":"SimVS: Simulating World Inconsistencies for Robust View Synthesis","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2204.09171","title":"Learned Monocular Depth Priors in Visual-Inertial Initialization","created":"2022-04-20","cited_by_count":4,"area":null},{"id":"2207.06351","title":"Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometry","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2208.02709","title":"Globally Consistent Video Depth and Pose Estimation with Efficient Test-Time Training","created":"2022-08-04","cited_by_count":4,"area":null},{"id":"2304.05716","title":"Impact of Pseudo Depth on Open World Object Segmentation with Minimal User Guidance","created":"2023-04-12","cited_by_count":4,"area":null},{"id":"2406.09374","title":"Scale-Invariant Monocular Depth Estimation via SSI Depth","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2409.15010","title":"DepthART: Monocular Depth Estimation as Autoregressive Refinement Task","created":"2024-09-23","cited_by_count":4,"area":"diffusion"},{"id":"2108.13408","title":"View Synthesis of Dynamic Scenes based on Deep 3D Mask Volume","created":"2021-08-30","cited_by_count":3,"area":null},{"id":"2205.02930","title":"FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras","created":"2022-05-05","cited_by_count":3,"area":null},{"id":"2210.01886","title":"Multi-view Human Body Mesh Translator","created":"2022-10-04","cited_by_count":3,"area":null},{"id":"2510.07119","title":"MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2103.12496","title":"Revisiting Self-Supervised Monocular Depth Estimation","created":"2021-03-23","cited_by_count":2,"area":null},{"id":"2306.05428","title":"Background Prompting for Improved Object Depth","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2312.08071","title":"Novel View Synthesis with View-Dependent Effects from a Single Image","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2410.11330","title":"Evolutionary Retrofitting","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2512.05113","title":"Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2103.02521","title":"On the role of depth predictions for 3D human pose estimation","created":"2021-03-03","cited_by_count":1,"area":null},{"id":"2103.16706","title":"DynOcc: Learning Single-View Depth from Dynamic Occlusion Cues","created":"2021-03-30","cited_by_count":1,"area":null}],"next_cursor":"100"}