{"list":"other","total":52,"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2312.06741","title":"Gaussian Splatting SLAM","created":"2023-12-11","cited_by_count":415},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2410.24207","title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","created":"2024-10-31","cited_by_count":248},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"2306.05422","title":"Tracking Everything Everywhere All at Once","created":"2023-06-08","cited_by_count":193},{"id":"1905.02082","title":"ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals","created":"2019-05-06","cited_by_count":181},{"id":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179},{"id":"2302.03594","title":"NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM","created":"2023-02-07","cited_by_count":164},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144},{"id":"2407.15208","title":"Flow as the Cross-Domain Manipulation Interface","created":"2024-07-21","cited_by_count":132},{"id":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117},{"id":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89},{"id":"2504.13152","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World","created":"2025-04-17","cited_by_count":89},{"id":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79},{"id":"2408.01654","title":"Deep Patch Visual SLAM","created":"2024-08-03","cited_by_count":71},{"id":"2406.07472","title":"4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models","created":"2024-06-11","cited_by_count":64},{"id":"2406.00434","title":"MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors","created":"2024-06-01","cited_by_count":51},{"id":"1910.00130","title":"Track to Reconstruct and Reconstruct to Track","created":"2019-09-30","cited_by_count":49},{"id":"2412.03526","title":"Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos","created":"2024-12-04","cited_by_count":49},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49},{"id":"2501.14914","title":"Light3R-SfM: Towards Feed-forward Structure-from-Motion","created":"2025-01-24","cited_by_count":47},{"id":"2112.08177","title":"Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry","created":"2021-12-15","cited_by_count":46},{"id":"2503.16318","title":"Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction","created":"2025-03-20","cited_by_count":44},{"id":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35},{"id":"2412.09072","title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","created":"2024-12-12","cited_by_count":30},{"id":"1708.04398","title":"Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames","created":"2017-08-15","cited_by_count":27},{"id":"2501.10357","title":"Zero-Shot Monocular Scene Flow Estimation in the Wild","created":"2025-01-17","cited_by_count":22},{"id":"1603.03381","title":"Temporally coherent 4D reconstruction of complex dynamic scenes","created":"2016-03-10","cited_by_count":21},{"id":"2512.04021","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","created":"2025-12-03","cited_by_count":21},{"id":"2506.09997","title":"DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos","created":"2025-06-11","cited_by_count":15},{"id":"2510.08575","title":"ReSplat: Learning Recurrent Gaussian Splatting","created":"2025-10-09","cited_by_count":15},{"id":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","cited_by_count":10}],"next_cursor":null}