{"list":"other","total":78,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"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":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2103.15595","title":"MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo","created":"2021-03-29","cited_by_count":740},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"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":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"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":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","cited_by_count":364},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"2111.14643","title":"Urban Radiance Fields","created":"2021-11-29","cited_by_count":263},{"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":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"id":"2111.13539","title":"GeoNeRF: Generalizing NeRF with Geometry Priors","created":"2021-11-26","cited_by_count":196},{"id":"2107.13421","title":"Neural Rays for Occlusion-aware Image-based Rendering","created":"2021-07-28","cited_by_count":192},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"2408.13912","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-08-25","cited_by_count":178},{"id":"2008.04838","title":"TransNet V2: An effective deep network architecture for fast shot transition detection","created":"2020-08-11","cited_by_count":171},{"id":"2004.01294","title":"Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera","created":"2020-04-02","cited_by_count":166},{"id":"2311.12024","title":"PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction","created":"2023-11-20","cited_by_count":165},{"id":"2403.15704","title":"Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections","created":"2024-03-23","cited_by_count":117},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114},{"id":"2302.00833","title":"RobustNeRF: Ignoring Distractors with Robust Losses","created":"2023-02-02","cited_by_count":101},{"id":"2405.18715","title":"NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild","created":"2024-05-29","cited_by_count":85},{"id":"2108.03151","title":"Full-Duplex Strategy for Video Object Segmentation","created":"2021-08-06","cited_by_count":78},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77},{"id":"1604.00136","title":"It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos","created":"2016-04-01","cited_by_count":71},{"id":"2310.01410","title":"LEAP: Liberate Sparse-view 3D Modeling from Camera Poses","created":"2023-10-02","cited_by_count":65},{"id":"2003.04253","title":"Motion-Attentive Transition for Zero-Shot Video Object Segmentation","created":"2020-03-09","cited_by_count":62},{"id":"2403.10427","title":"SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians","created":"2024-03-15","cited_by_count":61},{"id":"2406.20055","title":"SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":61},{"id":"2406.10373","title":"Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections","created":"2024-06-14","cited_by_count":56},{"id":"2212.04492","title":"Few-View Object Reconstruction with Unknown Categories and Camera Poses","created":"2022-12-08","cited_by_count":53},{"id":"2504.03886","title":"WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments","created":"2025-04-04","cited_by_count":50},{"id":"2111.06394","title":"The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos","created":"2021-11-11","cited_by_count":45},{"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":"2308.14710","title":"VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation","created":"2023-08-28","cited_by_count":37},{"id":"2406.09371","title":"LRM-Zero: Training Large Reconstruction Models with Synthesized Data","created":"2024-06-13","cited_by_count":35},{"id":"2503.22268","title":"Segment Any Motion in Videos","created":"2025-03-28","cited_by_count":35},{"id":"2406.02407","title":"WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections","created":"2024-06-04","cited_by_count":33},{"id":"2403.17537","title":"NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation","created":"2024-03-26","cited_by_count":25},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22},{"id":"2510.13063","title":"True Self-Supervised Novel View Synthesis is Transferable","created":"2025-10-15","cited_by_count":15},{"id":"2007.06620","title":"AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation","created":"2020-07-13","cited_by_count":14},{"id":"2506.18890","title":"4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time","created":"2025-06-23","cited_by_count":14},{"id":"2412.00155","title":"T-3DGS: Removing Transient Objects for 3D Scene Reconstruction","created":"2024-11-29","cited_by_count":13},{"id":"1804.02142","title":"Motion Segmentation by Exploiting Complementary Geometric Models","created":"2018-04-06","cited_by_count":9},{"id":"2411.19141","title":"On Moving Object Segmentation from Monocular Video with Transformers","created":"2024-11-28","cited_by_count":6},{"id":"2405.01723","title":"Zero-Shot Monocular Motion Segmentation in the Wild by Combining Deep Learning with Geometric Motion Model Fusion","created":"2024-05-02","cited_by_count":4}],"next_cursor":null}