{"list":"other","total":66,"rows":[{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2104.00674","title":"PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting","created":"2021-04-01","cited_by_count":335},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286},{"id":"2112.00390","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","created":"2021-12-01","cited_by_count":280},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"1905.02722","title":"Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image","created":"2019-05-07","cited_by_count":203},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"id":"2312.03594","title":"A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting","created":"2023-12-06","cited_by_count":169},{"id":"2405.00666","title":"RGB$\\leftrightarrow$X: Image decomposition and synthesis using material- and lighting-aware diffusion models","created":"2024-05-01","cited_by_count":161},{"id":"2406.16864","title":"StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal","created":"2024-06-24","cited_by_count":154},{"id":"1905.00824","title":"Single Image Portrait Relighting","created":"2019-05-02","cited_by_count":152},{"id":"2108.11515","title":"Robust High-Resolution Video Matting with Temporal Guidance","created":"2021-08-25","cited_by_count":137},{"id":"2011.11961","title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","created":"2020-11-24","cited_by_count":127},{"id":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124},{"id":"2402.17113","title":"Transparent Image Layer Diffusion using Latent Transparency","created":"2024-02-27","cited_by_count":114},{"id":"2004.00626","title":"Background Matting: The World is Your Green Screen","created":"2020-04-01","cited_by_count":105},{"id":"1901.02453","title":"Neural Inverse Rendering of an Indoor Scene from a Single Image","created":"2019-01-08","cited_by_count":101},{"id":"2211.03017","title":"Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing","created":"2022-11-06","cited_by_count":78},{"id":"2403.13788","title":"DepthFM: Fast Monocular Depth Estimation with Flow Matching","created":"2024-03-20","cited_by_count":76},{"id":"1804.00582","title":"Learning Intrinsic Image Decomposition from Watching the World","created":"2018-04-02","cited_by_count":74},{"id":"2403.06090","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","created":"2024-03-10","cited_by_count":74},{"id":"2312.12274","title":"Intrinsic Image Diffusion for Indoor Single-view Material Estimation","created":"2023-12-19","cited_by_count":73},{"id":"1704.04131","title":"Neural Face Editing with Intrinsic Image Disentangling","created":"2017-04-13","cited_by_count":70},{"id":"2404.11593","title":"IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination","created":"2024-04-17","cited_by_count":67},{"id":"1707.05055","title":"Information-Flow Matting","created":"2017-07-17","cited_by_count":59},{"id":"1806.06503","title":"Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance","created":"2018-06-18","cited_by_count":58},{"id":"2410.10815","title":"Depth Any Video with Scalable Synthetic Data","created":"2024-10-14","cited_by_count":57},{"id":"1911.09930","title":"Unsupervised Learning for Intrinsic Image Decomposition from a Single Image","created":"2019-11-22","cited_by_count":55},{"id":"2311.12792","title":"Intrinsic Image Decomposition via Ordinal Shading","created":"2023-11-21","cited_by_count":53},{"id":"2409.13690","title":"Colorful Diffuse Intrinsic Image Decomposition in the Wild","created":"2024-09-20","cited_by_count":44},{"id":"2411.16318","title":"One Diffusion to Generate Them All","created":"2024-11-25","cited_by_count":41},{"id":"2502.17157","title":"DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks","created":"2025-02-24","cited_by_count":39},{"id":"2411.16683","title":"Generative Omnimatte: Learning to Decompose Video into Layers","created":"2024-11-25","cited_by_count":38},{"id":"2504.01016","title":"GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors","created":"2025-04-01","cited_by_count":37},{"id":"1803.04636","title":"TOM-Net: Learning Transparent Object Matting from a Single Image","created":"2018-03-13","cited_by_count":34},{"id":"2411.17864","title":"Generative Image Layer Decomposition with Visual Effects","created":"2024-11-26","cited_by_count":34},{"id":"2402.02771","title":"TensoSDF: Roughness-aware Tensorial Representation for Robust Geometry and Material Reconstruction","created":"2024-02-05","cited_by_count":26},{"id":"2504.11427","title":"NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors","created":"2025-04-15","cited_by_count":25},{"id":"2501.14677","title":"MatAnyone: Stable Video Matting with Consistent Memory Propagation","created":"2025-01-24","cited_by_count":24},{"id":"2310.06347","title":"JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling","created":"2023-10-10","cited_by_count":23},{"id":"1803.00805","title":"Unsupervised Deep Single-Image Intrinsic Decomposition using Illumination-Varying Image Sequences","created":"2018-03-02","cited_by_count":22},{"id":"2208.12801","title":"VMFormer: End-to-End Video Matting with Transformer","created":"2022-08-26","cited_by_count":20},{"id":"2412.04460","title":"LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors","created":"2024-12-05","cited_by_count":19},{"id":"2504.01008","title":"IntrinsiX: High-Quality PBR Generation using Image Priors","created":"2025-04-01","cited_by_count":19},{"id":"2404.16035","title":"MaGGIe: Masked Guided Gradual Human Instance Matting","created":"2024-04-24","cited_by_count":18},{"id":"2508.14461","title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","created":"2025-08-20","cited_by_count":16},{"id":"2412.15050","title":"Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion","created":"2024-12-19","cited_by_count":15},{"id":"2504.14219","title":"PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling","created":"2025-04-19","cited_by_count":9},{"id":"2505.24521","title":"UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation","created":"2025-05-30","cited_by_count":9},{"id":"2511.01767","title":"Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image","created":"2025-11-03","cited_by_count":8},{"id":"2110.07145","title":"SpongeCake: A Layered Microflake Surface Appearance Model","created":"2021-10-14","cited_by_count":5},{"id":"2505.19084","title":"Jodi: Unification of Visual Generation and Understanding via Joint Modeling","created":"2025-05-25","cited_by_count":5},{"id":"2510.23574","title":"More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models","created":"2025-10-27","cited_by_count":2}],"next_cursor":null}