{"total":412,"rows":[{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843,"area":null},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739,"area":null},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412,"area":"diffusion"},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326,"area":null},{"id":"2302.01721","title":"TEXTure: Text-Guided Texturing of 3D Shapes","created":"2023-02-03","cited_by_count":304,"area":"diffusion"},{"id":"2504.05118","title":"VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks","created":"2025-04-07","cited_by_count":285,"area":"lr"},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220,"area":null},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188,"area":null},{"id":"2211.13752","title":"Sketch-Guided Text-to-Image Diffusion Models","created":"2022-11-24","cited_by_count":180,"area":"diffusion"},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133,"area":null},{"id":"2212.00968","title":"UIU-Net: U-Net in U-Net for Infrared Small Object Detection","created":"2022-12-02","cited_by_count":127,"area":null},{"id":"2401.03407","title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","created":"2024-01-07","cited_by_count":112,"area":null},{"id":"2101.06046","title":"Counterfactual Generative Networks","created":"2021-01-15","cited_by_count":111,"area":null},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110,"area":null},{"id":"2103.00762","title":"NeuTex: Neural Texture Mapping for Volumetric Neural Rendering","created":"2021-03-01","cited_by_count":98,"area":null},{"id":"2402.11929","title":"DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation","created":"2024-02-19","cited_by_count":93,"area":"diffusion"},{"id":"2205.15768","title":"SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections","created":"2022-05-31","cited_by_count":89,"area":null},{"id":"2109.07193","title":"FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack","created":"2021-09-15","cited_by_count":74,"area":null},{"id":"2403.06090","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","created":"2024-03-10","cited_by_count":74,"area":"diffusion"},{"id":"2211.17256","title":"CLIPascene: Scene Sketching with Different Types and Levels of Abstraction","created":"2022-11-30","cited_by_count":64,"area":null},{"id":"2401.01256","title":"VideoStudio: Generating Consistent-Content and Multi-Scene Videos","created":"2024-01-02","cited_by_count":64,"area":"diffusion"},{"id":"2408.08870","title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","created":"2024-08-16","cited_by_count":64,"area":null},{"id":"2204.05041","title":"Pyramid Grafting Network for One-Stage High Resolution Saliency Detection","created":"2022-04-11","cited_by_count":63,"area":null},{"id":"2207.01322","title":"Harmonizer: Learning to Perform White-Box Image and Video Harmonization","created":"2022-07-04","cited_by_count":61,"area":null},{"id":"2107.05274","title":"TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation","created":"2021-07-12","cited_by_count":60,"area":null},{"id":"2107.07235","title":"Deep Automatic Natural Image Matting","created":"2021-07-15","cited_by_count":59,"area":null},{"id":"2202.05822","title":"CLIPasso: Semantically-Aware Object Sketching","created":"2022-02-11","cited_by_count":57,"area":null},{"id":"2403.12034","title":"VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models","created":"2024-03-18","cited_by_count":56,"area":"diffusion"},{"id":"2303.09813","title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","created":"2023-03-17","cited_by_count":54,"area":"diffusion"},{"id":"2203.13458","title":"PANDORA: Polarization-Aided Neural Decomposition Of Radiance","created":"2022-03-25","cited_by_count":52,"area":null},{"id":"2401.09416","title":"TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion","created":"2024-01-17","cited_by_count":52,"area":null},{"id":"2212.03863","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","created":"2022-12-07","cited_by_count":49,"area":null},{"id":"2109.01068","title":"SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting","created":"2021-09-02","cited_by_count":48,"area":null},{"id":"2109.12484","title":"Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation","created":"2021-09-26","cited_by_count":48,"area":"distill"},{"id":"2101.03694","title":"Learning to Segment Rigid Motions from Two Frames","created":"2021-01-11","cited_by_count":46,"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":"2210.09420","title":"Differentiable Physics Simulation of Dynamics-Augmented Neural Objects","created":"2022-10-17","cited_by_count":45,"area":null},{"id":"2111.08446","title":"Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions","created":"2021-11-03","cited_by_count":43,"area":null},{"id":"2101.04704","title":"Boundary-Aware Segmentation Network for Mobile and Web Applications","created":"2021-01-12","cited_by_count":42,"area":null},{"id":"2111.03216","title":"Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network","created":"2021-11-05","cited_by_count":42,"area":null},{"id":"2110.12942","title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","created":"2021-10-25","cited_by_count":39,"area":null},{"id":"2101.06175","title":"PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation","created":"2021-01-15","cited_by_count":35,"area":null},{"id":"2309.03493","title":"SAM3D: Segment Anything Model in Volumetric Medical Images","created":"2023-09-07","cited_by_count":34,"area":null},{"id":"2105.13864","title":"SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Staging","created":"2021-05-24","cited_by_count":32,"area":null},{"id":"2408.13509","title":"Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation","created":"2024-08-24","cited_by_count":32,"area":"diffusion"},{"id":"2401.05735","title":"Object-Centric Diffusion for Efficient Video Editing","created":"2024-01-11","cited_by_count":31,"area":"diffusion"},{"id":"2106.05121","title":"Grounding inductive biases in natural images:invariance stems from variations in data","created":"2021-06-09","cited_by_count":27,"area":null},{"id":"2210.08161","title":"Geometric Representation Learning for Document Image Rectification","created":"2022-10-15","cited_by_count":27,"area":null},{"id":"2303.09604","title":"DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion","created":"2023-03-16","cited_by_count":26,"area":"diffusion"},{"id":"2407.01092","title":"Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies","created":"2024-07-01","cited_by_count":26,"area":null},{"id":"2110.14968","title":"DocScanner: Robust Document Image Rectification with Progressive Learning","created":"2021-10-28","cited_by_count":25,"area":null},{"id":"2305.11577","title":"LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model","created":"2023-05-19","cited_by_count":25,"area":"diffusion"},{"id":"2404.15677","title":"CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models","created":"2024-04-24","cited_by_count":24,"area":"diffusion"},{"id":"2404.04996","title":"Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM","created":"2024-04-07","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":"2409.07179","title":"Phy124: Fast Physics-Driven 4D Content Generation from a Single Image","created":"2024-09-11","cited_by_count":23,"area":"diffusion"},{"id":"2411.16800","title":"Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception","created":"2024-11-25","cited_by_count":23,"area":null},{"id":"2503.23452","title":"VideoGen-Eval: Agent-based System for Video Generation Evaluation","created":"2025-03-30","cited_by_count":23,"area":"agents"},{"id":"2401.12051","title":"CloSe: A 3D Clothing Segmentation Dataset and Model","created":"2024-01-22","cited_by_count":22,"area":null},{"id":"2410.08063","title":"Reversible Decoupling Network for Single Image Reflection Removal","created":"2024-10-10","cited_by_count":22,"area":null},{"id":"2412.14173","title":"AniDoc: Animation Creation Made Easier","created":"2024-12-18","cited_by_count":22,"area":null},{"id":"2210.16898","title":"Attention Swin U-Net: Cross-Contextual Attention Mechanism for Skin Lesion Segmentation","created":"2022-10-30","cited_by_count":21,"area":null},{"id":"2306.07596","title":"Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model","created":"2023-06-13","cited_by_count":21,"area":"diffusion"},{"id":"2104.01526","title":"Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images","created":"2021-04-04","cited_by_count":20,"area":null},{"id":"2105.13865","title":"Recursive Contour Saliency Blending Network for Accurate Salient Object Detection","created":"2021-05-28","cited_by_count":20,"area":null},{"id":"2205.11283","title":"SelfReformer: Self-Refined Network with Transformer for Salient Object Detection","created":"2022-05-23","cited_by_count":20,"area":null},{"id":"2206.00048","title":"PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs","created":"2022-05-31","cited_by_count":20,"area":null},{"id":"2105.03053","title":"Salient Objects in Clutter","created":"2021-05-07","cited_by_count":19,"area":null},{"id":"2403.09093","title":"Desigen: A Pipeline for Controllable Design Template Generation","created":"2024-03-14","cited_by_count":19,"area":null},{"id":"2303.06138","title":"Learning Object-Centric Neural Scattering Functions for Free-Viewpoint Relighting and Scene Composition","created":"2023-03-10","cited_by_count":17,"area":null},{"id":"2303.10396","title":"Towards Diverse Binary Segmentation via A Simple yet General Gated Network","created":"2023-03-18","cited_by_count":17,"area":null},{"id":"2307.14052","title":"Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation","created":"2023-07-26","cited_by_count":17,"area":null},{"id":"2309.13646","title":"ILNet: Low-level Matters for Salient Infrared Small Target Detection","created":"2023-09-24","cited_by_count":17,"area":null},{"id":"2104.00858","title":"Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction","created":"2021-04-02","cited_by_count":16,"area":null},{"id":"2104.09701","title":"Free-form tumor synthesis in computed tomography images via richer generative adversarial network","created":"2021-04-20","cited_by_count":16,"area":null},{"id":"2112.01932","title":"Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images","created":"2021-12-02","cited_by_count":16,"area":null},{"id":"2304.08796","title":"Deep Unrestricted Document Image Rectification","created":"2023-04-18","cited_by_count":16,"area":null},{"id":"2308.16635","title":"MFR-Net: Multi-faceted Responsive Listening Head Generation via Denoising Diffusion Model","created":"2023-08-31","cited_by_count":16,"area":"diffusion"},{"id":"2408.00418","title":"Towards Reliable Advertising Image Generation Using Human Feedback","created":"2024-08-01","cited_by_count":16,"area":null},{"id":"2103.00334","title":"BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection","created":"2021-02-27","cited_by_count":15,"area":null},{"id":"2310.14532","title":"Practical Deep Dispersed Watermarking with Synchronization and Fusion","created":"2023-10-23","cited_by_count":15,"area":null},{"id":"2404.15700","title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","created":"2024-04-24","cited_by_count":15,"area":null},{"id":"2405.10185","title":"DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data","created":"2024-05-16","cited_by_count":15,"area":null},{"id":"2212.04965","title":"Seeing a Rose in Five Thousand Ways","created":"2022-12-09","cited_by_count":13,"area":null},{"id":"2212.06458","title":"HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping","created":"2022-12-13","cited_by_count":13,"area":"diffusion"},{"id":"2212.12378","title":"Multi-Projection Fusion and Refinement Network for Salient Object Detection in 360{\\deg} Omnidirectional Image","created":"2022-12-23","cited_by_count":13,"area":null},{"id":"2301.05211","title":"Accidental Light Probes","created":"2023-01-12","cited_by_count":13,"area":null},{"id":"2302.10167","title":"Cross-domain Compositing with Pretrained Diffusion Models","created":"2023-02-20","cited_by_count":13,"area":"diffusion"},{"id":"2303.10894","title":"M$^{2}$SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation","created":"2023-03-20","cited_by_count":13,"area":null},{"id":"2311.17609","title":"Curved Diffusion: A Generative Model With Optical Geometry Control","created":"2023-11-29","cited_by_count":13,"area":"diffusion"},{"id":"2501.18588","title":"Inkspire: Supporting Design Exploration with Generative AI through Analogical Sketching","created":"2025-01-30","cited_by_count":13,"area":null},{"id":"2212.02096","title":"FBLNet: FeedBack Loop Network for Driver Attention Prediction","created":"2022-12-05","cited_by_count":12,"area":null},{"id":"2305.14955","title":"DC-Net: Divide-and-Conquer for Salient Object Detection","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2312.04566","title":"Gen2Det: Generate to Detect","created":"2023-12-07","cited_by_count":12,"area":"diffusion"},{"id":"2503.21745","title":"3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models","created":"2025-03-27","cited_by_count":12,"area":null},{"id":"2508.04190","title":"RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation","created":"2025-08-06","cited_by_count":12,"area":null},{"id":"2105.02646","title":"Cascade Image Matting with Deformable Graph Refinement","created":"2021-05-06","cited_by_count":11,"area":null},{"id":"2206.12837","title":"Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer","created":"2022-06-26","cited_by_count":11,"area":null},{"id":"2207.10183","title":"2D GANs Meet Unsupervised Single-view 3D Reconstruction","created":"2022-07-20","cited_by_count":11,"area":null}],"next_cursor":"100"}