Optimizing Few-Shot Novel View Synthesis with Human-Perceptual Preferences.
TL;DR
Human Perceptual Preference Optimization is introduced, a framework that incorporates human perceptual guidance into model training and mitigates distortions by regularizing training dynamics with perceptual preference cues, thereby reducing the reliance on extensive supervised views.
Abstract
Novel view synthesis methods, such as neural radiance fields and 3D Gaussian splatting, offer a promising solution for photorealistic rendering. However, they remain challenged in few-shot settings, where models tend to overfit the limited supervised views, leading to artifacts such as quality fluctuations, degradation in distant views, and geometric inconsistencies. To address these issues, we introduce Human Perceptual Preference Optimization (HuPPO), a framework that incorporates human perceptual guidance into model training. HuPPO mitigates distortions by regularizing training dynamics with perceptual preference cues, thereby reducing the reliance on extensive supervised views. Specifically, HuPPO leverages human perception to identify and select candidate novel views, and introduces a corresponding objective function that steers optimization toward perceptually preferred outcomes. In addition, a meta-learning pipeline is integrated to promote the learning of generalizable representations. The framework is flexible and can be seamlessly applied to a wide range of neural rendering models without incurring additional inference overhead. Extensive experiments and analyses demonstrate that HuPPO achieves consistent improvements over state-of-the-art baselines.