paper-with-me

Papers

VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos

2024-09-11 · Yan-Bo Lin, Yu Tian, Linjie Yang, Gedas Bertasius, Heng Wang

We present a framework for learning to generate background music from video inputs. Unlike existing works that rely on symbolic musical annotations, which are limited in quantity and diversity, our method leverages large-scale web videos accompanied by background music. This enables our model to learn to generate realistic and diverse music. To accomplish this goal, we develop a generative video-music Transformer with a novel semantic video-music alignment scheme. Our model uses a joint autoregressive and contrastive learning objective, which encourages the generation of music aligned with high-level video content. We also introduce a novel video-beat alignment scheme to match the generated music beats with the low-level motions in the video. Lastly, to capture fine-grained visual cues in a video needed for realistic background music generation, we introduce a new temporal video encoder architecture, allowing us to efficiently process videos consisting of many densely sampled frames. We train our framework on our newly curated DISCO-MV dataset, consisting of 2.2M video-music samples, which is orders of magnitude larger than any prior datasets used for video music generation. Our method outperforms existing approaches on the DISCO-MV and MusicCaps datasets according to various music generation evaluation metrics, including human evaluation. Results are available at https://genjib.github.io/project_page/VMAs/index.html

📄 PDF Abstract BibTeX arXiv:2409.07450

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningMusic Generation

Methods 이 논문이 사용한 방법론

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation

2026-03-11 · Yan-Bo Lin, Jonah Casebeer, Long Mai, Aniruddha Mahapatra 외 arxiv

Generating music that temporally aligns with video events is challenging for existing text-to-music models, which lack fine-grained temporal control. We introduce V2M-ZERO, a video-to-music generation approach that gener…

Music Generation

Video-Robin: Autoregressive Diffusion Planning for Intent-Grounded Video-to-Music Generation

2026-04-19 · Vaibhavi Lokegaonkar, Aryan Vijay Bhosale, Vishnu Raj, Gouthaman KV 외 arxiv

Video-to-music (V2M) is the fundamental task of creating background music for an input video. Recent V2M models achieve audiovisual alignment by typically relying on visual conditioning alone and provide limited semantic…

Music Generation

Towards Video to Piano Music Generation with Chain-of-Perform Support Benchmarks

2025-05-26 · Chang Liu, Haomin Zhang, Shiyu Xia, Zihao Chen 외

Generating high-quality piano audio from video requires precise synchronization between visual cues and musical output, ensuring accurate semantic and temporal alignment.However, existing evaluation datasets do not fully…

Music Generation

Diff-BGM: A Diffusion Model for Video Background Music Generation

2024-05-20 · CVPR 2024 1 · Sizhe Li, Yiming Qin, Minghang Zheng, Xin Jin 외

When editing a video, a piece of attractive background music is indispensable. However, video background music generation tasks face several challenges, for example, the lack of suitable training datasets, and the diffic…

DiversityMusic GenerationRhythm

Extending Visual Dynamics for Video-to-Music Generation

2025-04-10 · Xiaohao Liu, Teng Tu, Yunshan Ma, Tat-Seng Chua

Music profoundly enhances video production by improving quality, engagement, and emotional resonance, sparking growing interest in video-to-music generation. Despite recent advances, existing approaches remain limited in…

Music GenerationOptical Flow Estimation