Random Weight Factorization Improves the Training of Continuous Neural Representations
원문 초록
Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and computationally expensive. Here we propose random weight factorization as a simple drop-in replacement for parameterizing and initializing conventional linear layers in coordinate-based multi-layer perceptrons (MLPs) that significantly accelerates and improves their training. We show how this factorization alters the underlying loss landscape and effectively enables each neuron in the network to learn using its own self-adaptive learning rate. This not only helps with mitigating spectral bias, but also allows networks to quickly recover from poor initializations and reach better local minima. We demonstrate how random weight factorization can be leveraged to improve the training of neural representations on a variety of tasks, including image regression, shape representation, computed tomography, inverse rendering, solving partial differential equations, and learning operators between function spaces.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splatting
SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering
TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering
Shadow Art Kanji: Inverse Rendering Application
ROSA: Reconstructing Object Shape and Appearance Textures by Adaptive Detail Transfer
Materialist: Physically Based Editing Using Single-Image Inverse Rendering
토론
이 논문과 연결된 포럼 글이 아직 없습니다.