{"list":"other","total":72,"rows":[{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"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":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"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":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"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":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2307.08581","title":"BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs","created":"2023-07-17","cited_by_count":114},{"id":"2004.09476","title":"Music Gesture for Visual Sound Separation","created":"2020-04-20","cited_by_count":112},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"2010.05466","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","created":"2020-10-12","cited_by_count":104},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101},{"id":"2506.04225","title":"Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation","created":"2025-06-04","cited_by_count":101},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"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":"2404.06903","title":"DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting","created":"2024-04-10","cited_by_count":82},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73},{"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":"1812.04204","title":"2.5D Visual Sound","created":"2018-12-11","cited_by_count":63},{"id":"2011.01143","title":"Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds","created":"2020-11-02","cited_by_count":55},{"id":"1908.11602","title":"Recursive Visual Sound Separation Using Minus-Plus Net","created":"2019-08-30","cited_by_count":53},{"id":"2408.13252","title":"LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation","created":"2024-08-23","cited_by_count":53},{"id":"2211.12131","title":"DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models","created":"2022-11-22","cited_by_count":51},{"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":"2309.10724","title":"Sound Source Localization is All about Cross-Modal Alignment","created":"2023-09-19","cited_by_count":31},{"id":"2407.01851","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","created":"2024-07-01","cited_by_count":26},{"id":"2506.01799","title":"WorldExplorer: Towards Generating Fully Navigable 3D Scenes","created":"2025-06-02","cited_by_count":26},{"id":"1805.04792","title":"Scene-Aware Audio for 360\\textdegree{} Videos","created":"2018-05-12","cited_by_count":25},{"id":"2005.07074","title":"FaceFilter: Audio-visual speech separation using still images","created":"2020-05-14","cited_by_count":25},{"id":"2405.18424","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting","created":"2024-05-28","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":"2207.10141","title":"AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation","created":"2022-07-20","cited_by_count":24},{"id":"2407.15187","title":"HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions","created":"2024-07-21","cited_by_count":24},{"id":"2405.17842","title":"MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation","created":"2024-05-28","cited_by_count":23},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22},{"id":"2504.14906","title":"OmniAudio: Generating Spatial Audio from 360-Degree Video","created":"2025-04-21","cited_by_count":17},{"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":"2504.10001","title":"GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting","created":"2025-04-14","cited_by_count":6},{"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":"2505.23625","title":"ZeroSep: Separate Anything in Audio with Zero Training","created":"2025-05-29","cited_by_count":4},{"id":"2510.26800","title":"OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes","created":"2025-10-30","cited_by_count":4}],"next_cursor":null}