{"list":"other","total":51,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245},{"id":"2311.13384","title":"LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes","created":"2023-11-22","cited_by_count":231},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202},{"id":"2407.14358","title":"Stable Audio Open","created":"2024-07-19","cited_by_count":197},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158},{"id":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133},{"id":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110},{"id":"2412.12091","title":"Wonderland: Navigating 3D Scenes from a Single Image","created":"2024-12-16","cited_by_count":99},{"id":"2404.09956","title":"Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization","created":"2024-04-15","cited_by_count":97},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"2012.09854","title":"Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image","created":"2020-12-17","cited_by_count":77},{"id":"2412.21037","title":"TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization","created":"2024-12-30","cited_by_count":68},{"id":"2204.00628","title":"Learning Neural Acoustic Fields","created":"2022-04-04","cited_by_count":65},{"id":"1704.08292","title":"Deep Cross-Modal Audio-Visual Generation","created":"2017-04-26","cited_by_count":63},{"id":"2302.02088","title":"AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis","created":"2023-02-04","cited_by_count":49},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49},{"id":"2508.16930","title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","created":"2025-08-23","cited_by_count":46},{"id":"2505.18151","title":"WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions","created":"2025-05-23","cited_by_count":45},{"id":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","cited_by_count":44},{"id":"2301.08730","title":"Novel-View Acoustic Synthesis","created":"2023-01-20","cited_by_count":33},{"id":"2403.09439","title":"3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation","created":"2024-03-14","cited_by_count":29},{"id":"1805.04792","title":"Scene-Aware Audio for 360\\textdegree{} Videos","created":"2018-05-12","cited_by_count":25},{"id":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25},{"id":"2309.15977","title":"Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fields","created":"2023-09-27","cited_by_count":23},{"id":"2504.14906","title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","created":"2025-04-21","cited_by_count":17},{"id":"2411.00626","title":"ZIM: Zero-Shot Image Matting for Anything","created":"2024-11-01","cited_by_count":16},{"id":"2406.08920","title":"AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis","created":"2024-06-13","cited_by_count":14},{"id":"2411.06307","title":"Acoustic Volume Rendering for Neural Impulse Response Fields","created":"2024-11-09","cited_by_count":14},{"id":"2406.07532","title":"Hearing Anything Anywhere","created":"2024-06-11","cited_by_count":12},{"id":"2410.14945","title":"ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model","created":"2024-10-19","cited_by_count":11},{"id":"2506.12199","title":"ViSAGe: Video-to-Spatial Audio Generation","created":"2025-06-13","cited_by_count":11},{"id":"2406.06612","title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound","created":"2024-06-06","cited_by_count":10},{"id":"2504.10746","title":"Hearing Anywhere in Any Environment","created":"2025-04-14","cited_by_count":8},{"id":"2506.15759","title":"Sonic4D: Spatial Audio Generation for Immersive 4D Scene Exploration","created":"2025-06-18","cited_by_count":6},{"id":"2504.21847","title":"Differentiable Room Acoustic Rendering with Multi-View Vision Priors","created":"2025-04-30","cited_by_count":5},{"id":"2504.05576","title":"SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Binding","created":"2025-04-08","cited_by_count":3},{"id":"2506.20367","title":"DreamAnywhere: Object-Centric Panoramic 3D Scene Generation","created":"2025-06-25","cited_by_count":2}],"next_cursor":null}