{"list":"other","total":65,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2011.12100","title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","created":"2020-11-24","cited_by_count":785},{"id":"2411.15098","title":"OminiControl: Minimal and Universal Control for Diffusion Transformer","created":"2024-11-22","cited_by_count":340},{"id":"2311.14521","title":"GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting","created":"2023-11-24","cited_by_count":335},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136},{"id":"2503.07027","title":"EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer","created":"2025-03-10","cited_by_count":119},{"id":"2411.14430","title":"Stable Flow: Vital Layers for Training-Free Image Editing","created":"2024-11-21","cited_by_count":113},{"id":"2312.07536","title":"FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition","created":"2023-12-12","cited_by_count":91},{"id":"2203.14954","title":"GIRAFFE HD: A High-Resolution 3D-aware Generative Model","created":"2022-03-28","cited_by_count":86},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2312.03079","title":"LooseControl: Lifting ControlNet for Generalized Depth Conditioning","created":"2023-12-05","cited_by_count":68},{"id":"2312.02190","title":"Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D","created":"2023-12-02","cited_by_count":59},{"id":"2503.08280","title":"OminiControl2: Efficient Conditioning for Diffusion Transformers","created":"2025-03-11","cited_by_count":57},{"id":"2503.13439","title":"Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images","created":"2025-03-17","cited_by_count":54},{"id":"2311.17137","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","created":"2023-11-28","cited_by_count":50},{"id":"2312.17247","title":"Amodal Ground Truth and Completion in the Wild","created":"2023-12-28","cited_by_count":45},{"id":"2401.01702","title":"Image Sculpting: Precise Object Editing with 3D Geometry Control","created":"2024-01-02","cited_by_count":45},{"id":"2412.18605","title":"Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models","created":"2024-12-24","cited_by_count":45},{"id":"2404.14403","title":"GeoDiffuser: Geometry-Based Image Editing with Diffusion Models","created":"2024-04-22","cited_by_count":34},{"id":"2406.09292","title":"Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models","created":"2024-06-13","cited_by_count":30},{"id":"2405.18424","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting","created":"2024-05-28","cited_by_count":25},{"id":"1905.11826","title":"Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion","created":"2019-05-28","cited_by_count":24},{"id":"2402.14792","title":"Consolidating Attention Features for Multi-view Image Editing","created":"2024-02-22","cited_by_count":19},{"id":"2503.12652","title":"UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing","created":"2025-03-16","cited_by_count":19},{"id":"2507.04961","title":"InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior","created":"2025-07-07","cited_by_count":19},{"id":"2408.14819","title":"Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation","created":"2024-08-27","cited_by_count":18},{"id":"2406.07706","title":"Object-level Scene Deocclusion","created":"2024-06-11","cited_by_count":17},{"id":"2402.08654","title":"Learning Continuous 3D Words for Text-to-Image Generation","created":"2024-02-13","cited_by_count":16},{"id":"2409.14677","title":"Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections","created":"2024-09-23","cited_by_count":16},{"id":"2302.06608","title":"3D-aware Blending with Generative NeRFs","created":"2023-02-13","cited_by_count":13},{"id":"2501.12910","title":"PreciseCam: Precise Camera Control for Text-to-Image Generation","created":"2025-01-22","cited_by_count":13},{"id":"2403.11503","title":"Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors","created":"2024-03-18","cited_by_count":12},{"id":"2505.10566","title":"3D-Fixup: Advancing Photo Editing with 3D Priors","created":"2025-05-15","cited_by_count":12},{"id":"2407.15446","title":"Text2Place: Affordance-aware Text Guided Human Placement","created":"2024-07-22","cited_by_count":11},{"id":"2504.06752","title":"Compass Control: Multi Object Orientation Control for Text-to-Image Generation","created":"2025-04-09","cited_by_count":11},{"id":"2508.07647","title":"LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering","created":"2025-08-11","cited_by_count":11},{"id":"2503.22194","title":"ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation","created":"2025-03-28","cited_by_count":10},{"id":"2511.16666","title":"SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation","created":"2025-11-20","cited_by_count":9},{"id":"2303.14706","title":"BlobGAN-3D: A Spatially-Disentangled 3D-Aware Generative Model for Indoor Scenes","created":"2023-03-26","cited_by_count":8},{"id":"2408.07540","title":"3D Gaussian Editing with A Single Image","created":"2024-08-14","cited_by_count":8},{"id":"2503.06261","title":"Segment Anything, Even Occluded","created":"2025-03-08","cited_by_count":7},{"id":"2507.03257","title":"LACONIC: A 3D Layout Adapter for Controllable Image Creation","created":"2025-07-04","cited_by_count":6},{"id":"2409.10775","title":"Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?","created":"2024-09-16","cited_by_count":5},{"id":"2412.02336","title":"Amodal Depth Anything: Amodal Depth Estimation in the Wild","created":"2024-12-03","cited_by_count":5},{"id":"2501.04374","title":"Instructive3D: Editing Large Reconstruction Models with Text Instructions","created":"2025-01-08","cited_by_count":5},{"id":"2407.17205","title":"The Sketchfab 3D Creative Commons Collection (S3D3C)","created":"2024-07-24","cited_by_count":4},{"id":"2504.06801","title":"MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection","created":"2025-04-09","cited_by_count":4},{"id":"2504.06432","title":"D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition","created":"2025-04-08","cited_by_count":2},{"id":"2510.23956","title":"Neural USD: An object-centric framework for iterative editing and control","created":"2025-10-28","cited_by_count":2},{"id":"2508.08498","title":"CObL: Toward Zero-Shot Ordinal Layering without User Prompting","created":"2025-08-11","cited_by_count":1}],"next_cursor":null}