TV-AudioRemover: Joint Text-Visual Guided Sound Removal with Multi-Task Hard-Mixture Curriculum

arXiv:2609.25864 · cs.MM, cs.CV, cs.SD · Submitted 2026-09-22 · Read on arXiv

cs.MM, cs.CV, cs.SD

Submitted: 2026-09-22

Updated: 2026-09-22

Project page: https://yjx-research.github.io/TV-AudioRemover

Terminology

• Fidelity — 22× in this paper · explained in 2 episodes
• Benchmark — 13× in this paper · explained in 2 episodes
• Consistency — 10× in this paper · explained in 3 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Embeddings — 3× in this paper · explained in 2 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action Groups — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Anchor Source — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Joint Attention — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Preserved Source Fidelity — 1× in this paper
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• From Understanding to Erasing: Towards Complete and Stable Video Object Removal
• From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
• Schrodinger Audio-Visual Editor: Object-Level Audiovisual Removal
• SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing
• Coherent Audio-Visual Editing via Conditional Audio Generation Following Video Edits
• MMEDIT: A Unified Framework for Multi-Type Audio Editing via Audio Language Model
• SAM Audio: Segment Anything in Audio
• Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion
• DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast
• AudioMorphix: Training-free audio editing with diffusion probabilistic models
• Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
• UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion
• Unified Audio Generation and Editing via Joint Condition Modeling and Progressive Training
• Object-AVEdit: An Object-level Audio-Visual Editing Model
• InstructAV2AV: Instruction-Guided Audio-Video Joint Editing
• JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation
• Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
• Seedance 2.0: Advancing Video Generation for World Complexity
• AST: Audio Spectrogram Transformer
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Related papers

• ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
• Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models
• Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection
• A Rate-Distortion-Classification Approach for Lossy Image Compression