{"list":"other","total":69,"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"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":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"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":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"id":"2312.02981","title":"ReconFusion: 3D Reconstruction with Diffusion Priors","created":"2023-12-05","cited_by_count":318},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2210.04628","title":"Novel View Synthesis with Diffusion Models","created":"2022-10-06","cited_by_count":300},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286},{"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":"2204.07143","title":"Neighborhood Attention Transformer","created":"2022-04-14","cited_by_count":239},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","cited_by_count":227},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"id":"2312.07504","title":"COLMAP-Free 3D Gaussian Splatting","created":"2023-12-12","cited_by_count":193},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2401.11605","title":"Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers","created":"2024-01-21","cited_by_count":118},{"id":"2411.04924","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","created":"2024-11-07","cited_by_count":116},{"id":"2401.12592","title":"RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos","created":"2024-01-23","cited_by_count":115},{"id":"2507.16443","title":"VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences","created":"2025-07-22","cited_by_count":115},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"id":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77},{"id":"2407.07860","title":"Controlling Space and Time with Diffusion Models","created":"2024-07-10","cited_by_count":66},{"id":"2412.01821","title":"World-consistent Video Diffusion with Explicit 3D Modeling","created":"2024-12-02","cited_by_count":65},{"id":"2410.22128","title":"PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting","created":"2024-10-29","cited_by_count":62},{"id":"2303.14478","title":"DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields","created":"2023-03-25","cited_by_count":60},{"id":"1807.08957","title":"The Double Sphere Camera Model","created":"2018-07-24","cited_by_count":52},{"id":"2211.14306","title":"RUST: Latent Neural Scene Representations from Unposed Imagery","created":"2022-11-25","cited_by_count":43},{"id":"2411.17190","title":"SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting","created":"2024-11-26","cited_by_count":42},{"id":"2508.01171","title":"No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views","created":"2025-08-02","cited_by_count":40},{"id":"2306.00180","title":"FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow","created":"2023-05-31","cited_by_count":39},{"id":"2110.02951","title":"Video Autoencoder: self-supervised disentanglement of static 3D structure and motion","created":"2021-10-06","cited_by_count":34},{"id":"2502.03738","title":"Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More","created":"2025-02-06","cited_by_count":28},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22},{"id":"2501.07574","title":"UnCommon Objects in 3D","created":"2025-01-13","cited_by_count":17},{"id":"2509.21302","title":"Quantized Visual Geometry Grounded Transformer","created":"2025-09-25","cited_by_count":17},{"id":"2411.07765","title":"Novel View Synthesis with Pixel-Space Diffusion Models","created":"2024-11-12","cited_by_count":16},{"id":"2503.10286","title":"VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames","created":"2025-03-13","cited_by_count":15},{"id":"2510.13063","title":"True Self-Supervised Novel View Synthesis is Transferable","created":"2025-10-15","cited_by_count":15},{"id":"2310.06020","title":"DyST: Towards Dynamic Neural Scene Representations on Real-World Videos","created":"2023-10-09","cited_by_count":11},{"id":"2304.00947","title":"RePAST: Relative Pose Attention Scene Representation Transformer","created":"2023-04-03","cited_by_count":8},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8},{"id":"2509.17246","title":"SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views","created":"2025-09-21","cited_by_count":7},{"id":"2509.06950","title":"Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data","created":"2025-09-08","cited_by_count":4},{"id":"2505.13440","title":"Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos","created":"2025-05-19","cited_by_count":3}],"next_cursor":null}