Pith. sign in

REVIEW 18 cited by

FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.01494 v1 pith:GYRKPWCM submitted 2024-07-01 cs.CV cs.SDeess.AS

FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds

classification cs.CV cs.SDeess.AS
keywords foleycraftergenerationsemanticadapterhigh-qualitytemporalachievealignment
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We study Neural Foley, the automatic generation of high-quality sound effects synchronizing with videos, enabling an immersive audio-visual experience. Despite its wide range of applications, existing approaches encounter limitations when it comes to simultaneously synthesizing high-quality and video-aligned (i.e.,, semantic relevant and temporal synchronized) sounds. To overcome these limitations, we propose FoleyCrafter, a novel framework that leverages a pre-trained text-to-audio model to ensure high-quality audio generation. FoleyCrafter comprises two key components: the semantic adapter for semantic alignment and the temporal controller for precise audio-video synchronization. The semantic adapter utilizes parallel cross-attention layers to condition audio generation on video features, producing realistic sound effects that are semantically relevant to the visual content. Meanwhile, the temporal controller incorporates an onset detector and a timestampbased adapter to achieve precise audio-video alignment. One notable advantage of FoleyCrafter is its compatibility with text prompts, enabling the use of text descriptions to achieve controllable and diverse video-to-audio generation according to user intents. We conduct extensive quantitative and qualitative experiments on standard benchmarks to verify the effectiveness of FoleyCrafter. Models and codes are available at https://github.com/open-mmlab/FoleyCrafter.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

    cs.SD 2025-12 accept novelty 8.0

    PhyAVBench supplies the first benchmark and contrastive metric that measures whether text-to-audio-video models respect real-world audio physics across controlled prompt pairs.

  2. Benchmarking Single-Factor Physical Video-to-Audio Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    FlatSounds benchmark shows state-of-the-art V2A models rely more on text captions than visual input for physical and semantic accuracy, with captions improving correctness but degrading temporal alignment.

  3. LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV

    cs.CV 2026-05 unverdicted novelty 7.0

    LongAV-Compass is a new benchmark and evaluation framework for minute-scale audio-visual generation across T2AV, I2AV, and V2AV with multi-dimensional assessment.

  4. Geo2Sound: A Scalable Geo-Aligned Framework for Soundscape Generation from Satellite Imagery

    cs.MM 2026-04 unverdicted novelty 7.0

    Geo2Sound generates geographically realistic soundscapes from satellite imagery via geospatial attribute modeling, semantic hypothesis expansion, and geo-acoustic alignment, achieving SOTA FAD of 1.765 on a new 20k-pa...

  5. FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips

    cs.CV 2026-04 unverdicted novelty 7.0

    FoleyDesigner generates spatio-temporally aligned stereo Foley audio for film clips via multi-agent analysis, diffusion models on video cues, and LLM mixing, supported by the new FilmStereo dataset.

  6. OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text

    cs.SD 2026-04 unverdicted novelty 7.0

    OmniSonic introduces a TriAttn-DiT architecture with MoE gating to jointly generate on-screen, off-screen, and speech audio from video and text, outperforming prior models on a new UniHAGen-Bench.

  7. PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

    cs.SD 2025-12 unverdicted novelty 7.0

    PhyAVBench provides the first systematic benchmark and metric for audio-physics grounding in T2AV, I2AV, and V2A models using controlled prompt pairs and real video ground truth.

  8. MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection

    cs.CV 2025-11 conditional novelty 7.0

    MVAD is the first comprehensive benchmark dataset for AI-generated multimodal video-audio detection, with three realistic forgery patterns, high-quality outputs from state-of-the-art models, and diversity across visua...

  9. AudioMoG: Guiding Audio Generation with Mixture-of-Guidance

    cs.SD 2025-09 unverdicted novelty 7.0

    AudioMoG is a mixture-of-guidance sampling technique that combines CFG and AG signals to outperform single-guidance baselines in text-to-audio generation at equivalent speed.

  10. StereoFoley: Object-Aware Stereo Audio Generation from Video

    cs.SD 2025-09 conditional novelty 7.0

    StereoFoley is an end-to-end video-to-stereo-audio framework that uses a base generative model fine-tuned on synthetic object-tracked data with panning and distance controls to achieve object-aware spatial sound.

  11. Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space

    cs.MM 2026-07 conditional novelty 6.0

    A single-stage flow-based V2A model with progressive soft-masked cross-attention achieves SOTA on VGGSound and approaches a 13B closed model's audio quality with 169M parameters.

  12. MMAudio-LABEL: Audio Event Labeling via Audio Generation for Silent Video

    cs.SD 2026-05 unverdicted novelty 6.0

    MMAudio-LABEL jointly generates audio and sound event labels from silent videos, raising onset detection accuracy to 75.0% and material classification to 61.0% on the Greatest Hits dataset.

  13. Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models

    cs.CV 2026-02 unverdicted novelty 6.0

    MMHNet enables video-to-audio models trained on short clips to generalize and generate audio for videos over 5 minutes long.

  14. Aliasing-Free Neural Audio Synthesis

    cs.SD 2025-12 conditional novelty 6.0

    Pupu-Vocoder and Pupu-Codec integrate differentiable anti-aliasing into neural audio models to eliminate aliasing artifacts from non-linear activations and upsampling, yielding better results on music and singing voice.

  15. NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation

    cs.CV 2025-10 unverdicted novelty 6.0

    NoiseShift learns a resolution-specific mapping from scheduler noise to conditioning noise via lightweight calibration to restore consistency and improve low-resolution generation quality in models like SD3 and Flux.

  16. AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation

    cs.SD 2026-06 unverdicted novelty 5.0

    AudioX-Turbo distills a Multimodal Diffusion Transformer into a 4-step student model for efficient multimodal anything-to-audio generation, trained on a new 9.2M-sample dataset IF-caps-Pro.

  17. LTX-2: Efficient Joint Audio-Visual Foundation Model

    cs.CV 2026-01 conditional novelty 5.0

    LTX-2 generates high-quality synchronized audiovisual content from text prompts via an asymmetric 14B-video / 5B-audio dual-stream transformer with cross-attention and modality-aware guidance.

  18. MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation

    cs.SD 2025-10 unverdicted novelty 4.0

    MMAudioSep adapts a pretrained video-to-audio model via fine-tuning for video/text-queried sound separation, outperforming baselines while preserving generation ability.