{"total":353,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863,"area":null},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422,"area":null},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983,"area":null},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657,"area":null},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575,"area":null},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327,"area":null},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327,"area":"diffusion"},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286,"area":"diffusion"},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286,"area":null},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275,"area":null},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243,"area":null},{"id":"2401.01339","title":"Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting","created":"2024-01-02","cited_by_count":221,"area":"wm"},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207,"area":null},{"id":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173,"area":null},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172,"area":null},{"id":"2307.15058","title":"MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving","created":"2023-07-27","cited_by_count":170,"area":null},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166,"area":"diffusion"},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164,"area":"diffusion"},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161,"area":null},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160,"area":null},{"id":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150,"area":null},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123,"area":"diffusion"},{"id":"2406.01493","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","created":"2024-06-03","cited_by_count":100,"area":"diffusion"},{"id":"2507.02863","title":"Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory","created":"2025-07-03","cited_by_count":87,"area":null},{"id":"2409.11355","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","created":"2024-09-17","cited_by_count":83,"area":"diffusion"},{"id":"2505.09358","title":"Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis","created":"2025-05-14","cited_by_count":78,"area":"diffusion"},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2111.03042","title":"Unsupervised Learning of Compositional Energy Concepts","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67,"area":"wm"},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2204.07616","title":"Multi-Frame Self-Supervised Depth with Transformers","created":"2022-04-15","cited_by_count":64,"area":null},{"id":"2409.00638","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","created":"2024-09-01","cited_by_count":59,"area":null},{"id":"2108.03830","title":"Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark","created":"2021-08-09","cited_by_count":58,"area":null},{"id":"2410.10815","title":"Depth Any Video with Scalable Synthetic Data","created":"2024-10-14","cited_by_count":57,"area":"diffusion"},{"id":"2501.09466","title":"DEFOM-Stereo: Depth Foundation Model Based Stereo Matching","created":"2025-01-16","cited_by_count":52,"area":null},{"id":"2510.07316","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","created":"2025-10-08","cited_by_count":51,"area":"diffusion"},{"id":"2511.15706","title":"RoMa v2: Harder Better Faster Denser Feature Matching","created":"2025-11-19","cited_by_count":51,"area":null},{"id":"2412.13389","title":"Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion","created":"2024-12-18","cited_by_count":50,"area":"diffusion"},{"id":"2304.12205","title":"Synthetic Datasets for Autonomous Driving: A Survey","created":"2023-04-24","cited_by_count":48,"area":null},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46,"area":"wm"},{"id":"2204.00179","title":"GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature","created":"2022-04-01","cited_by_count":43,"area":null},{"id":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43,"area":null},{"id":"2104.02253","title":"Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries","created":"2021-04-06","cited_by_count":41,"area":null},{"id":"2308.14713","title":"R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras","created":"2023-08-28","cited_by_count":39,"area":null},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39,"area":null},{"id":"2504.01016","title":"GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors","created":"2025-04-01","cited_by_count":37,"area":"diffusion"},{"id":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2503.07535","title":"LBM: Latent Bridge Matching for Fast Image-to-Image Translation","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2505.10696","title":"TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation","created":"2025-05-15","cited_by_count":36,"area":null},{"id":"2406.03175","title":"Dynamic 3D Gaussian Fields for Urban Areas","created":"2024-06-05","cited_by_count":35,"area":"wm"},{"id":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35,"area":null},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2103.16694","title":"Geometric Unsupervised Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":33,"area":null},{"id":"2503.14405","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","created":"2025-03-18","cited_by_count":32,"area":"distill"},{"id":"2203.15089","title":"Learning Optical Flow, Depth, and Scene Flow without Real-World Labels","created":"2022-03-28","cited_by_count":31,"area":null},{"id":"2409.15278","title":"PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions","created":"2024-09-23","cited_by_count":31,"area":null},{"id":"2604.08542","title":"Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction","created":"2026-04-09","cited_by_count":31,"area":null},{"id":"2204.01403","title":"How stable are Transferability Metrics evaluations?","created":"2022-04-04","cited_by_count":30,"area":null},{"id":"2407.17952","title":"BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation","created":"2024-07-25","cited_by_count":28,"area":null},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2207.01610","title":"PVO: Panoptic Visual Odometry","created":"2022-07-04","cited_by_count":26,"area":null},{"id":"2412.15213","title":"Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution","created":"2024-12-19","cited_by_count":26,"area":"diffusion"},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2304.02163","title":"GINA-3D: Learning to Generate Implicit Neural Assets in the Wild","created":"2023-04-04","cited_by_count":25,"area":null},{"id":"2509.26618","title":"DA$^{2}$: Depth Anything in Any Direction","created":"2025-09-30","cited_by_count":25,"area":null},{"id":"2103.12209","title":"Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervision","created":"2021-03-22","cited_by_count":24,"area":null},{"id":"2401.08045","title":"Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities","created":"2024-01-16","cited_by_count":24,"area":"driving"},{"id":"2509.04338","title":"From Editor to Dense Geometry Estimator","created":"2025-09-04","cited_by_count":24,"area":"diffusion"},{"id":"2103.15254","title":"Bayesian Deep Basis Fitting for Depth Completion with Uncertainty","created":"2021-03-29","cited_by_count":23,"area":null},{"id":"2406.08249","title":"Dataset Enhancement with Instance-Level Augmentations","created":"2024-06-12","cited_by_count":23,"area":"diffusion"},{"id":"2407.07816","title":"A Survey on Deep Stereo Matching in the Twenties","created":"2024-07-10","cited_by_count":23,"area":null},{"id":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23,"area":null},{"id":"2204.09788","title":"SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints","created":"2022-04-20","cited_by_count":22,"area":null},{"id":"2407.08711","title":"OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects","created":"2024-07-11","cited_by_count":22,"area":null},{"id":"2410.19590","title":"MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors","created":"2024-10-25","cited_by_count":22,"area":null},{"id":"2511.10560","title":"OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer","created":"2025-11-13","cited_by_count":22,"area":null},{"id":"2503.15905","title":"Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation","created":"2025-03-20","cited_by_count":21,"area":"diffusion"},{"id":"2308.14619","title":"Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation","created":"2023-08-28","cited_by_count":20,"area":null},{"id":"2508.17972","title":"SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization","created":"2025-08-25","cited_by_count":20,"area":null},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20,"area":null},{"id":"2112.03241","title":"Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey","created":"2021-12-06","cited_by_count":19,"area":null},{"id":"2404.13816","title":"Neural Radiance Field in Autonomous Driving: A Survey","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2501.02576","title":"DepthMaster: Taming Diffusion Models for Monocular Depth Estimation","created":"2025-01-05","cited_by_count":19,"area":"diffusion"},{"id":"2508.14717","title":"GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting","created":"2025-08-20","cited_by_count":18,"area":"diffusion"},{"id":"2512.01030","title":"Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model","created":"2025-11-30","cited_by_count":18,"area":"diffusion"},{"id":"2308.10079","title":"MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance","created":"2023-08-19","cited_by_count":17,"area":"diffusion"},{"id":"2512.04939","title":"LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging","created":"2025-12-04","cited_by_count":17,"area":"inference"},{"id":"2211.08658","title":"Consistent Direct Time-of-Flight Video Depth Super-Resolution","created":"2022-11-16","cited_by_count":16,"area":null},{"id":"2312.00944","title":"Enhancing Diffusion Models with 3D Perspective Geometry Constraints","created":"2023-12-01","cited_by_count":16,"area":"diffusion"},{"id":"2103.12964","title":"Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation","created":"2021-03-24","cited_by_count":15,"area":null},{"id":"2304.03526","title":"Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field","created":"2023-04-07","cited_by_count":15,"area":null},{"id":"2401.11414","title":"S$^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving","created":"2024-01-21","cited_by_count":15,"area":null},{"id":"2407.08187","title":"ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation","created":"2024-07-11","cited_by_count":15,"area":null},{"id":"2308.12372","title":"Vision Transformer Adapters for Generalizable Multitask Learning","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2507.04631","title":"Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts","created":"2025-07-07","cited_by_count":14,"area":"moe"},{"id":"2404.18620","title":"FlexiFilm: Long Video Generation with Flexible Conditions","created":"2024-04-29","cited_by_count":13,"area":"diffusion"},{"id":"2412.08410","title":"Physical Informed Driving World Model","created":"2024-12-11","cited_by_count":13,"area":"wm"},{"id":"2505.18992","title":"VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes","created":"2025-05-25","cited_by_count":13,"area":null}],"next_cursor":"100"}