{"total":50,"rows":[{"id":"2311.15937","title":"Optimal Transport Aggregation for Visual Place Recognition","created":"2023-11-27","cited_by_count":152,"area":null},{"id":"2504.06632","title":"PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering","created":"2025-04-09","cited_by_count":46,"area":null},{"id":"2405.08672","title":"EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera","created":"2024-05-14","cited_by_count":43,"area":null},{"id":"2306.04121","title":"Matte Anything: Interactive Natural Image Matting with Segment Anything Models","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2404.02790","title":"MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation","created":"2024-04-03","cited_by_count":38,"area":null},{"id":"2501.14677","title":"MatAnyone: Stable Video Matting with Consistent Memory Propagation","created":"2025-01-24","cited_by_count":24,"area":null},{"id":"2503.17934","title":"TransAnimate: Taming Layer Diffusion to Generate RGBA Video","created":"2025-03-23","cited_by_count":24,"area":null},{"id":"2509.25134","title":"LayerD: Decomposing Raster Graphic Designs into Layers","created":"2025-09-29","cited_by_count":21,"area":null},{"id":"2408.14826","title":"Alfie: Democratising RGBA Image Generation With No $$$","created":"2024-08-27","cited_by_count":20,"area":null},{"id":"2503.07026","title":"Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways","created":"2025-03-10","cited_by_count":18,"area":null},{"id":"2411.00626","title":"ZIM: Zero-Shot Image Matting for Anything","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2403.12778","title":"ViTGaze: Gaze Following with Interaction Features in Vision Transformers","created":"2024-03-19","cited_by_count":15,"area":null},{"id":"2402.02941","title":"Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2501.03006","title":"TransPixeler: Advancing Text-to-Video Generation with Transparency","created":"2025-01-06","cited_by_count":12,"area":null},{"id":"2312.05915","title":"Diffusion for Natural Image Matting","created":"2023-12-10","cited_by_count":11,"area":null},{"id":"2503.10596","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","created":"2025-03-13","cited_by_count":11,"area":null},{"id":"2501.06230","title":"BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation","created":"2025-01-08","cited_by_count":7,"area":null},{"id":"2511.08251","title":"LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning","created":"2025-11-11","cited_by_count":7,"area":null},{"id":"2512.11782","title":"MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator","created":"2025-12-12","cited_by_count":7,"area":null},{"id":"2401.16861","title":"Repositioning the Subject within Image","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2405.19822","title":"Improving Object Detector Training on Synthetic Data by Starting With a Strong Baseline Methodology","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2406.12847","title":"ChangeViT: Unleashing Plain Vision Transformers for Change Detection","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2506.14315","title":"ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2408.10539","title":"Training Matting Models without Alpha Labels","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2412.13897","title":"Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2403.15789","title":"In-Context Matting","created":"2024-03-23","cited_by_count":3,"area":null},{"id":"2410.06593","title":"Towards Natural Image Matting in the Wild via Real-Scenario Prior","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2503.10697","title":"Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2602.19358","title":"Referring Layer Decomposition","created":"2026-02-22","cited_by_count":3,"area":null},{"id":"2605.18328","title":"CineMatte: Background Matting for Virtual Production and Beyond","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2410.10267","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2503.01262","title":"Object-Aware Video Matting with Cross-Frame Guidance","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2505.10294","title":"MIPHEI-ViT: Multiplex Immunofluorescence Prediction from H&E Images using ViT Foundation Models","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2601.03362","title":"Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2406.14412","title":"Benchmarking Monocular 3D Dog Pose Estimation Using In-The-Wild Motion Capture Data","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2408.12282","title":"Subsurface Scattering for 3D Gaussian Splatting","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2410.07600","title":"RNA: Video Editing with ROI-based Neural Atlas","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2501.16147","title":"Efficient Portrait Matte Creation With Layer Diffusion and Connectivity Priors","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2502.17093","title":"Enhancing Image Matting in Real-World Scenes with Mask-Guided Iterative Refinement","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2503.15917","title":"Learning to Efficiently Adapt Foundation Models for Self-Supervised Endoscopic 3D Scene Reconstruction from Any Cameras","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2402.15820","title":"DART: Depth-Enhanced Accurate and Real-Time Background Matting","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2506.10840","title":"Post-Training Quantization for Video Matting","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2507.05849","title":"DFYP: A Dynamic Fusion Framework with Spectral Channel Attention and Adaptive Operator learning for Crop Yield Prediction","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2507.07623","title":"Capture Stage Matting: Challenges, Approaches, and Solutions for Offline and Real-Time Processing","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2508.16026","title":"NeuralMeshing: Complete Object Mesh Extraction from Casual Captures","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2512.19331","title":"DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2605.24894","title":"BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.00386","title":"{\\alpha}Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.10395","title":"Self-supervised Automatic Matting","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.11205","title":"Parallax Portrait Matting","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}