{"total":267,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543,"area":null},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371,"area":null},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304,"area":null},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"area":null},{"id":"2311.02077","title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","created":"2023-11-03","cited_by_count":217,"area":null},{"id":"2301.09515","title":"StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis","created":"2023-01-23","cited_by_count":212,"area":null},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209,"area":null},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208,"area":null},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196,"area":null},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2204.00928","title":"SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image","created":"2022-04-02","cited_by_count":165,"area":null},{"id":"2308.00688","title":"AnyLoc: Towards Universal Visual Place Recognition","created":"2023-08-01","cited_by_count":163,"area":null},{"id":"2303.14536","title":"SUDS: Scalable Urban Dynamic Scenes","created":"2023-03-25","cited_by_count":151,"area":null},{"id":"2305.14093","title":"Weakly Supervised 3D Open-vocabulary Segmentation","created":"2023-05-23","cited_by_count":135,"area":null},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130,"area":null},{"id":"2403.10516","title":"FeatUp: A Model-Agnostic Framework for Features at Any Resolution","created":"2024-03-15","cited_by_count":116,"area":null},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112,"area":null},{"id":"2311.18809","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","created":"2023-11-30","cited_by_count":109,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2304.13348","title":"TextDeformer: Geometry Manipulation using Text Guidance","created":"2023-04-26","cited_by_count":94,"area":null},{"id":"2309.07970","title":"Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping","created":"2023-09-14","cited_by_count":91,"area":null},{"id":"2311.17034","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","created":"2023-11-28","cited_by_count":86,"area":null},{"id":"2401.01970","title":"FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding","created":"2024-01-03","cited_by_count":86,"area":null},{"id":"2209.08776","title":"NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes","created":"2022-09-19","cited_by_count":71,"area":null},{"id":"2401.07487","title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","created":"2024-01-15","cited_by_count":71,"area":null},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71,"area":null},{"id":"2207.03434","title":"LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery","created":"2022-07-07","cited_by_count":66,"area":null},{"id":"2212.07834","title":"Unsupervised Object Localization: Observing the Background to Discover Objects","created":"2022-12-15","cited_by_count":66,"area":null},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64,"area":null},{"id":"2403.14548","title":"DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video","created":"2024-03-21","cited_by_count":64,"area":null},{"id":"2406.20055","title":"SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting","created":"2024-06-28","cited_by_count":61,"area":null},{"id":"2204.03635","title":"Zero-Shot Category-Level Object Pose Estimation","created":"2022-04-07","cited_by_count":57,"area":null},{"id":"2311.17024","title":"Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features","created":"2023-11-28","cited_by_count":55,"area":null},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55,"area":null},{"id":"2305.11173","title":"Going Denser with Open-Vocabulary Part Segmentation","created":"2023-05-18","cited_by_count":51,"area":null},{"id":"2401.11673","title":"MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo","created":"2024-01-22","cited_by_count":50,"area":null},{"id":"2303.12786","title":"FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models","created":"2023-03-22","cited_by_count":47,"area":null},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45,"area":null},{"id":"2309.11986","title":"ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers","created":"2023-09-21","cited_by_count":45,"area":null},{"id":"2311.17776","title":"One-Shot Open Affordance Learning with Foundation Models","created":"2023-11-29","cited_by_count":45,"area":null},{"id":"2211.08089","title":"DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity","created":"2022-11-15","cited_by_count":38,"area":null},{"id":"2407.12957","title":"R+X: Retrieval and Execution from Everyday Human Videos","created":"2024-07-17","cited_by_count":38,"area":null},{"id":"2408.04961","title":"In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation","created":"2024-08-09","cited_by_count":38,"area":null},{"id":"2210.03043","title":"Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding","created":"2022-10-06","cited_by_count":37,"area":null},{"id":"2309.16118","title":"D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement","created":"2023-09-28","cited_by_count":35,"area":null},{"id":"2312.13216","title":"Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps","created":"2023-12-20","cited_by_count":34,"area":null},{"id":"2408.10123","title":"Learning Precise Affordances from Egocentric Videos for Robotic Manipulation","created":"2024-08-19","cited_by_count":34,"area":null},{"id":"2306.05410","title":"LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs","created":"2023-06-08","cited_by_count":33,"area":null},{"id":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2209.07147","title":"One-Shot Transfer of Affordance Regions? AffCorrs!","created":"2022-09-15","cited_by_count":31,"area":null},{"id":"2212.11042","title":"Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble","created":"2022-12-21","cited_by_count":31,"area":null},{"id":"2302.03956","title":"Neural Congealing: Aligning Images to a Joint Semantic Atlas","created":"2023-02-08","cited_by_count":31,"area":null},{"id":"2308.05737","title":"Follow Anything: Open-set detection, tracking, and following in real-time","created":"2023-08-10","cited_by_count":29,"area":null},{"id":"2506.16685","title":"Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections","created":"2025-06-20","cited_by_count":29,"area":null},{"id":"2210.03061","title":"Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal","created":"2022-10-06","cited_by_count":28,"area":null},{"id":"2303.16201","title":"ASIC: Aligning Sparse in-the-wild Image Collections","created":"2023-03-28","cited_by_count":27,"area":null},{"id":"2403.14625","title":"LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors","created":"2024-03-21","cited_by_count":27,"area":null},{"id":"2212.05853","title":"DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering","created":"2022-12-12","cited_by_count":25,"area":null},{"id":"2302.08509","title":"3D-aware Conditional Image Synthesis","created":"2023-02-16","cited_by_count":24,"area":null},{"id":"2307.03407","title":"Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation","created":"2023-07-07","cited_by_count":24,"area":null},{"id":"2307.03567","title":"SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks","created":"2023-07-07","cited_by_count":24,"area":null},{"id":"2308.16271","title":"Emergence of Segmentation with Minimalistic White-Box Transformers","created":"2023-08-30","cited_by_count":24,"area":null},{"id":"2209.14265","title":"360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidance","created":"2022-09-28","cited_by_count":23,"area":null},{"id":"2309.03173","title":"PDiscoNet: Semantically consistent part discovery for fine-grained recognition","created":"2023-09-06","cited_by_count":21,"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":"2210.07920","title":"MOVE: Unsupervised Movable Object Segmentation and Detection","created":"2022-10-14","cited_by_count":20,"area":null},{"id":"2311.00750","title":"Are These the Same Apple? Comparing Images Based on Object Intrinsics","created":"2023-11-01","cited_by_count":19,"area":null},{"id":"2507.23782","title":"MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2510.24709","title":"Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?","created":"2025-10-28","cited_by_count":19,"area":null},{"id":"2303.13396","title":"Zero-guidance Segmentation Using Zero Segment Labels","created":"2023-03-23","cited_by_count":18,"area":null},{"id":"2306.07598","title":"Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images","created":"2023-06-13","cited_by_count":18,"area":null},{"id":"2308.10417","title":"The Change You Want to See (Now in 3D)","created":"2023-08-21","cited_by_count":17,"area":null},{"id":"2409.06214","title":"Towards Generalizable Scene Change Detection","created":"2024-09-10","cited_by_count":17,"area":null},{"id":"2412.03512","title":"Distillation of Diffusion Features for Semantic Correspondence","created":"2024-12-04","cited_by_count":17,"area":null},{"id":"2310.12904","title":"Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey","created":"2023-10-19","cited_by_count":16,"area":null},{"id":"2404.13474","title":"Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models","created":"2024-04-20","cited_by_count":16,"area":null},{"id":"2406.04138","title":"The 3D-PC: a benchmark for visual perspective taking in humans and machines","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2405.18065","title":"EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition","created":"2024-05-28","cited_by_count":15,"area":null},{"id":"2501.12218","title":"Exploring Temporally-Aware Features for Point Tracking","created":"2025-01-21","cited_by_count":15,"area":null},{"id":"2312.01677","title":"Multi-task Image Restoration Guided By Robust DINO Features","created":"2023-12-04","cited_by_count":14,"area":null},{"id":"2403.00459","title":"Deformable One-shot Face Stylization via DINO Semantic Guidance","created":"2024-03-01","cited_by_count":14,"area":null},{"id":"2403.11120","title":"Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence","created":"2024-03-17","cited_by_count":14,"area":null},{"id":"2408.13575","title":"Can Visual Foundation Models Achieve Long-term Point Tracking?","created":"2024-08-24","cited_by_count":14,"area":null},{"id":"2409.15727","title":"LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation","created":"2024-09-24","cited_by_count":14,"area":null},{"id":"2411.19458","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","created":"2024-11-29","cited_by_count":14,"area":null},{"id":"2303.01526","title":"Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2309.04836","title":"Neural Semantic Surface Maps","created":"2023-09-09","cited_by_count":13,"area":null},{"id":"2404.15672","title":"Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision","created":"2024-04-24","cited_by_count":13,"area":null},{"id":"2506.05312","title":"Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2311.03784","title":"UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fields","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2312.06733","title":"TULIP: Transformer for Upsampling of LiDAR Point Clouds","created":"2023-12-11","cited_by_count":12,"area":null},{"id":"2405.14880","title":"Dissecting Query-Key Interaction in Vision Transformers","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2407.10084","title":"Part2Object: Hierarchical Unsupervised 3D Instance Segmentation","created":"2024-07-14","cited_by_count":12,"area":null},{"id":"2407.18907","title":"SHIC: Shape-Image Correspondences with no Keypoint Supervision","created":"2024-07-26","cited_by_count":12,"area":null},{"id":"2409.06210","title":"INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding","created":"2024-09-10","cited_by_count":12,"area":null},{"id":"2409.20563","title":"DressRecon: Freeform 4D Human Reconstruction from Monocular Video","created":"2024-09-30","cited_by_count":12,"area":null},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2505.21501","title":"Vision Transformers with Self-Distilled Registers","created":"2025-05-27","cited_by_count":12,"area":null}],"next_cursor":"100"}