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

arXiv: https://arxiv.org/abs/2609.25864 · HTML: https://mlsanity.com/paper/2609.25864/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion](https://mlsanity.com/paper/2402.10009/) (2024)
- [SAM Audio: Segment Anything in Audio](https://mlsanity.com/paper/2512.18099/) (2025)
- [Object-AVEdit: An Object-level Audio-Visual Editing Model](https://mlsanity.com/paper/2510.00050/) (2025)
- [Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing](https://mlsanity.com/paper/2604.10708/) (2026)
- [MMEDIT: A Unified Framework for Multi-Type Audio Editing via Audio Language Model](https://mlsanity.com/paper/2512.20339/) (2025)
- [SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing](https://mlsanity.com/paper/2605.25193/) (2026)
- [AudioMorphix: Training-free audio editing with diffusion probabilistic models](https://mlsanity.com/paper/2505.16076/) (2025)
- [Coherent Audio-Visual Editing via Conditional Audio Generation Following Video Edits](https://mlsanity.com/paper/2512.07209/) (2025)
- [From Ideal to Real: Stable Video Object Removal under Imperfect Conditions](https://mlsanity.com/paper/2603.09283/) (2026)
- [InstructAV2AV: Instruction-Guided Audio-Video Joint Editing](https://mlsanity.com/paper/2605.18467/) (2026)
- [Schrodinger Audio-Visual Editor: Object-Level Audiovisual Removal](https://mlsanity.com/paper/2512.12875/) (2025)
- [From Understanding to Erasing: Towards Complete and Stable Video Object Removal](https://mlsanity.com/paper/2604.01693/) (2026)
- [UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion](https://mlsanity.com/paper/2605.31530/) (2026)
- [JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation](https://mlsanity.com/paper/2606.03168/) (2026)
- [DirectAudioEdit: Inversion-Free Text-Guided Audio Editing via Diffusion Prediction Contrast](https://mlsanity.com/paper/2606.07356/) (2026)
- [Unified Audio Generation and Editing via Joint Condition Modeling and Progressive Training](https://mlsanity.com/paper/2606.16435/) (2026)

## Abstract (arXiv)

Visual object removal can eliminate a target from video frames, yet its acoustic trace persists in the soundtrack, causing obvious audio-visual inconsistency. Existing video inpainting models operate solely on pixels, while audio editing models, especially for the sound removal task, are typically driven by text and therefore rely on limited single-modal control, which is less effective than multimodal guidance that provides stronger semantic grounding and temporal synchronization cues. In this paper, we present Text-Visual Guided Sound Removal (TV-AudioRemover), a target sound removal framework that leverages the visually edited video together with a natural-language instruction to suppress the sound associated with the removed visual object from the original audio mixture. To acquire high-quality training data, we devise a pipeline to construct a million-scale dataset of single-object audio-visual aligned samples, from which we synthesize mixture-target pairs customized for model training. To effectively leverage visual context and follow instruction intent, we augment the model architecture with task tokens, generalizable instruction modeling, and modality-specific global guidance. We further adopt multi-task training to strengthen task-role comprehension, and employ a hard-mixture curriculum that leverages semantically similar acoustic mixtures during fine-tuning to enhance fine-grained source discrimination. To support evaluation, we present AV-Remove-Bench, a comprehensive audio-visual object removal benchmark, along with dedicated objective metrics and an MLLM-based evaluation protocol. Experiments demonstrate that our method achieves state-of-the-art performance on both subjective and objective metrics. Project page: https://yjx-research.github.io/TV-AudioRemover/.