提出可裁剪的隐式神经表示，支持无需重训练的信号删减。
Towards Croppable Implicit Neural Representations
- 通过局部-全局特征融合设计，实现信号裁剪时权重按比例衰减。
- 删除部分权重后仍保持完整编码，无需重新训练。
- 适用于图像、视频等多类信号，兼容INCODE等现代INR模型。
隐式神经表示（INRs）近年来受到广泛关注，因其能用神经网络编码自然信号。尽管INRs可用于坐标插值和信号压缩，但其黑箱特性使得训练后难以修改。本文探索可编辑INRs，聚焦于常见的裁剪操作。为此，提出一种名为局部-全局SIREN的新架构，天然支持裁剪。该架构结合局部与全局特征提取进行信号编码，其独特之处在于可轻松移除特定信号部分，对应权重按比例降低。通过直接删除网络中的相关权重即可实现，无需重新训练。我们进一步展示该架构如何简便扩展已有信号。除信号编辑外，还验证其可加速训练、提升各类信号编码效果，并改善下游性能，且可应用于INCODE等现代INR模型，展现其潜力与灵活性。代码已公开于https://github.com/maorash/Local-Global-INRs。
原文摘要 · Abstract (English)
Implicit Neural Representations (INRs) have peaked interest in recent years due to their ability to encode natural signals using neural networks. While INRs allow for useful applications such as interpolating new coordinates and signal compression, their black-box nature makes it difficult to modify them post-training. In this paper we explore the idea of editable INRs, and specifically focus on the widely used cropping operation. To this end, we present Local-Global SIRENs -- a novel INR architecture that supports cropping by design. Local-Global SIRENs are based on combining local and global feature extraction for signal encoding. What makes their design unique is the ability to effortlessly remove specific portions of an encoded signal, with a proportional weight decrease. This is achieved by eliminating the corresponding weights from the network, without the need for retraining. We further show how this architecture can be used to support the straightforward extension of previously encoded signals. Beyond signal editing, we examine how the Local-Global approach can accelerate training, enhance encoding of various signals, improve downstream performance, and be applied to modern INRs such as INCODE, highlighting its potential and flexibility. Code is available at https://github.com/maorash/Local-Global-INRs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。