Efficient Coordinate Representations for Large-Scale Neural Scene Localization and Rendering

Abstract

Neural Scene Representation depends on a defensible relationship between performance with evidence quality, resource limits, and transfer across settings. This technical review examines reducing optimization and rendering cost while preserving geometric and photometric consistency. The source set brings together 2 focal papers with 12 independently retrieved publications reviewed against traceable publication metadata. The analysis is organized around coordinate parameterization, mixture-of-experts, pose dependence, scene scale, and rendering fidelity. The comparison does not regard results from heterogeneous studies as exchangeable, the review compares problem boundaries, design logic, and conditions of validation. Across the literature, the literature consistently implies that advances in neural scene representation become credible when representation, objective, and evaluation protocol are evaluated together and when uncertainty about distribution shift is reported explicitly. The framework consequently connects method selection to downstream risk and the conditions that weaken external validity, and proposes a research agenda centered on clear comparators, adversarial conditions, and inspectable evidence.