Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields
Scale-ambiguity in 3D scene dimensions leads to magnitude-ambiguity of volumetric densities in neural radiance fields, i.e., the densities double when scene size is halved, and vice versa. We call this property alpha invariance. For NeRFs to better maintain alpha invariance, we recommend 1) parameterizing both distance and volume densities in log space, and 2) a discretization-agnostic initialization strategy to guarantee high ray transmittance. We revisit a few popular radiance field models and find that these systems use various heuristics to deal with issues arising from scene scaling. We test their behaviors and show our recipe to be more robust.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
Neural scaling laws are observed in a range of domains, to date with no clear understanding of why they occur. Recent theories suggest that loss power laws arise from Zipf's law, a power law observed in domains like natu…
Board GamesLanguage ModellingHyperReal: Complex-Valued Layer Functions For Complex-Valued Scaling Invariance
Complex-valued measurements in MRI and SAR imaging often have complex-valued scaling ambiguity, calling for models that are invariant to complex-valued scaling of pixels. Deep Complex Networks (DCN) extends real-valued a…
Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms
Since the emergence of research on improving the length extrapolation capabilities of large language models in 2021, some studies have made modifications to the scaling factor in the scaled dot-product attention mechanis…
Neural-network quantum state study of the long-range antiferromagnetic Ising chain
We investigate quantum phase transitions in the transverse field Ising chain with algebraically decaying long-range (LR) antiferromagnetic interactions using the variational Monte Carlo method with the restricted Boltzma…
Variational Monte CarloRevisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?
Geometric deep learning, i.e., designing neural networks to handle the ubiquitous geometric data such as point clouds and graphs, have achieved great successes in the last decade. One critical inductive bias is that the …
AllCombinatorial OptimizationGraph Neural NetworkInductive Bias