paper-with-me

Papers

Visual Acoustic Fields

2025-03-31 · Yuelei Li, HyunJin Kim, Fangneng Zhan, Ri-Zhao Qiu, Mazeyu Ji, Xiaojun Shan, Xueyan Zou, Paul Liang, Hanspeter Pfister, Xiaolong Wang

Objects produce different sounds when hit, and humans can intuitively infer how an object might sound based on its appearance and material properties. Inspired by this intuition, we propose Visual Acoustic Fields, a framework that bridges hitting sounds and visual signals within a 3D space using 3D Gaussian Splatting (3DGS). Our approach features two key modules: sound generation and sound localization. The sound generation module leverages a conditional diffusion model, which takes multiscale features rendered from a feature-augmented 3DGS to generate realistic hitting sounds. Meanwhile, the sound localization module enables querying the 3D scene, represented by the feature-augmented 3DGS, to localize hitting positions based on the sound sources. To support this framework, we introduce a novel pipeline for collecting scene-level visual-sound sample pairs, achieving alignment between captured images, impact locations, and corresponding sounds. To the best of our knowledge, this is the first dataset to connect visual and acoustic signals in a 3D context. Extensive experiments on our dataset demonstrate the effectiveness of Visual Acoustic Fields in generating plausible impact sounds and accurately localizing impact sources. Our project page is at https://yuelei0428.github.io/projects/Visual-Acoustic-Fields/.

📄 PDF Abstract BibTeX arXiv:2503.24270

Code (0)

등록된 구현이 없습니다.

Tasks

3DGS

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark

2024-03-27 · CVPR 2024 1 · Ziyang Chen, Israel D. Gebru, Christian Richardt, Anurag Kumar 외

We present a new dataset called Real Acoustic Fields (RAF) that captures real acoustic room data from multiple modalities. The dataset includes high-quality and densely captured room impulse response data paired with mul…

Few-Shot LearningPose TrackingResponse Generation

Learning Neural Acoustic Fields

2022-04-04 · Andrew Luo, Yilun Du, Michael J. Tarr, Joshua B. Tenenbaum 외

Our environment is filled with rich and dynamic acoustic information. When we walk into a cathedral, the reverberations as much as appearance inform us of the sanctuary's wide open space. Similarly, as an object moves ar…

NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields

2024-05-28 · Amandine Brunetto, Sascha Hornauer, Fabien Moutarde

Sound plays a major role in human perception. Along with vision, it provides essential information for understanding our surroundings. Despite advances in neural implicit representations, learning acoustics that align wi…

Novel View Synthesis

Pulsed Schlieren Imaging of Ultrasonic Haptics and Levitation using Phased Arrays

2018-09-29 · Michele Iodice, William Frier, James Wilcox, Ben Long 외

Ultrasonic acoustic fields have recently been used to generate haptic effects on the human skin as well as to levitate small sub-wavelength size particles. Schlieren imaging and background-oriented schlieren techniques c…

AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis

2023-02-04 · NeurIPS 2023 11

Can machines recording an audio-visual scene produce realistic, matching audio-visual experiences at novel positions and novel view directions? We answer it by studying a new task -- real-world audio-visual scene synthes…

3D geometryAudio GenerationNeRF