{"total":45,"rows":[{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230,"area":null},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150,"area":null},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101,"area":null},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2106.06650","title":"Large-Scale Unsupervised Object Discovery","created":"2021-06-12","cited_by_count":54,"area":null},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49,"area":null},{"id":"2205.07844","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","created":"2022-05-16","cited_by_count":42,"area":null},{"id":"2307.05473","title":"Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives","created":"2023-07-11","cited_by_count":38,"area":null},{"id":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38,"area":null},{"id":"2512.15603","title":"Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition","created":"2025-12-17","cited_by_count":34,"area":null},{"id":"2202.07135","title":"Compositional Scene Representation Learning via Reconstruction: A Survey","created":"2022-02-15","cited_by_count":27,"area":null},{"id":"2204.10310","title":"Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2509.25134","title":"LayerD: Decomposing Raster Graphic Designs into Layers","created":"2025-09-29","cited_by_count":21,"area":null},{"id":"2210.12148","title":"Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2207.02062","title":"Image Amodal Completion: A Survey","created":"2022-07-05","cited_by_count":18,"area":null},{"id":"2303.17842","title":"Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning","created":"2023-03-31","cited_by_count":17,"area":null},{"id":"2406.07706","title":"Object-level Scene Deocclusion","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2301.13197","title":"Unlocking Slot Attention by Changing Optimal Transport Costs","created":"2023-01-30","cited_by_count":16,"area":null},{"id":"2307.08027","title":"Multi-Object Discovery by Low-Dimensional Object Motion","created":"2023-07-16","cited_by_count":16,"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":"2402.07376","title":"Unsupervised Discovery of Object-Centric Neural Fields","created":"2024-02-12","cited_by_count":12,"area":null},{"id":"2205.13271","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2303.12533","title":"Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach","created":"2023-03-22","cited_by_count":8,"area":null},{"id":"2301.04101","title":"Neural Radiance Field Codebooks","created":"2023-01-10","cited_by_count":7,"area":null},{"id":"2110.03473","title":"Unsupervised Image Decomposition with Phase-Correlation Networks","created":"2021-10-07","cited_by_count":6,"area":null},{"id":"2210.02159","title":"Differentiable Mathematical Programming for Object-Centric Representation Learning","created":"2022-10-05","cited_by_count":6,"area":null},{"id":"2211.14308","title":"WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2304.09704","title":"Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans","created":"2023-04-19","cited_by_count":5,"area":null},{"id":"2411.00868","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2509.02545","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2302.01660","title":"The Learnable Typewriter: A Generative Approach to Text Analysis","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2408.03923","title":"Fast Sprite Decomposition from Animated Graphics","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2210.14139","title":"Learning Explicit Object-Centric Representations with Vision Transformers","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2211.11500","title":"Compositional Scene Modeling with Global Object-Centric Representations","created":"2022-11-21","cited_by_count":1,"area":null},{"id":"2308.13178","title":"Self-supervised Scene Text Segmentation with Object-centric Layered Representations Augmented by Text Regions","created":"2023-08-25","cited_by_count":1,"area":null},{"id":"2402.04558","title":"DMAT: A Dynamic Mask-Aware Transformer for Human De-occlusion","created":"2024-02-07","cited_by_count":1,"area":null},{"id":"2508.08498","title":"CObL: Toward Zero-Shot Ordinal Layering without User Prompting","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2407.11890","title":"DepGAN: Leveraging Depth Maps for Handling Occlusions and Transparency in Image Composition","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2408.08633","title":"Historical Printed Ornaments: Dataset and Tasks","created":"2024-08-16","cited_by_count":0,"area":null},{"id":"2506.19621","title":"VideoPCDNet: Video Parsing and Prediction with Phase Correlation Networks","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2604.19480","title":"Deep Sprite-based Image Models: An Analysis","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2606.09446","title":"Leveraging Morphology for Historical Script Metrological Analysis","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.07939","title":"Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}