AI RESEARCH
Optimizing Rank for High-Fidelity Implicit Neural Representations
arXiv CS.CV
•
ArXi:2512.14366v2 Announce Type: replace Implicit Neural Representations (INRs) based on vanilla Multi-Layer Perceptrons (MLPs) are widely believed to be incapable of representing high-frequency content. This has directed research efforts towards architectural interventions, such as coordinate embeddings or specialized activation functions, to represent high-frequency signals. In this paper, we challenge the notion that the low-frequency bias of vanilla MLPs is an intrinsic, architectural limitation to. We empirically nstrate that regulating the network's rank during.