# Non-Aligned Reference Image Quality Assessment for Novel View Synthesis

arXiv: https://arxiv.org/abs/2511.08155 · HTML: https://mlsanity.com/paper/2511.08155/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 30 of 31)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [PieAPP: Perceptual Image-Error Assessment through Pairwise Preference](https://mlsanity.com/paper/1806.02067/) (2018)
- [ARNIQA: Learning Distortion Manifold for Image Quality Assessment](https://mlsanity.com/paper/2310.14918/) (2023)
- [Shift-tolerant Perceptual Similarity Metric](https://mlsanity.com/paper/2207.13686/) (2022)
- [GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment](https://mlsanity.com/paper/2103.07666/) (2021)
- [NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer](https://mlsanity.com/paper/2303.06919/) (2023)
- [An Unsupervised Information-Theoretic Perceptual Quality Metric](https://mlsanity.com/paper/2006.06752/) (2020)
- [Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections](https://mlsanity.com/paper/2407.12306/) (2024)
- [Content-Variant Reference Image Quality Assessment via Knowledge Distillation](https://mlsanity.com/paper/2202.13123/) (2022)
- [DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluator](https://mlsanity.com/paper/2211.04927/) (2022)
- [Attacking Perceptual Similarity Metrics](https://mlsanity.com/paper/2305.08840/) (2023)
- [NeRF View Synthesis: Subjective Quality Assessment and Objective Metrics Evaluation](https://mlsanity.com/paper/2405.20078/) (2024)
- [NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods](https://mlsanity.com/paper/2412.08029/) (2024)
- [Transformer-based No-Reference Image Quality Assessment via Supervised Contrastive Learning](https://mlsanity.com/paper/2312.06995/) (2023)
- [Evaluating Human Perception of Novel View Synthesis: Subjective Quality Assessment of Gaussian Splatting and NeRF in Dynamic Scenes](https://mlsanity.com/paper/2501.08072/) (2025)
- [GS-QA: Comprehensive Quality Assessment Benchmark for Gaussian Splatting View Synthesis](https://mlsanity.com/paper/2502.13196/) (2025)
- [Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model Compression](https://mlsanity.com/paper/2407.08165/) (2024)
- [CrossScore: Towards Multi-View Image Evaluation and Scoring](https://mlsanity.com/paper/2404.14409/) (2024)
- [Foundation Models Boost Low-Level Perceptual Similarity Metrics](https://mlsanity.com/paper/2409.07650/) (2024)
- [LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model](https://mlsanity.com/paper/2408.17057/) (2024)
- [NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References](https://mlsanity.com/paper/2501.06488/) (2025)
- [TRIQA: Image Quality Assessment by Contrastive Pretraining on Ordered Distortion Triplets](https://mlsanity.com/paper/2507.12687/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment](https://mlsanity.com/paper/2609.07346/) (2026)

## Abstract (arXiv)

Evaluating the perceptual quality of Novel View Synthesis (NVS) images remains a key challenge, particularly in the absence of pixel-aligned ground truth references. Full-Reference Image Quality Assessment (FR-IQA) methods fail under misalignment, while No-Reference (NR-IQA) methods struggle with generalization. In this work, we introduce a Non-Aligned Reference (NAR-IQA) framework tailored for NVS, where it is assumed that the reference view shares partial scene content but lacks pixel-level alignment. We constructed a large-scale image dataset containing synthetic distortions targeting Temporal Regions of Interest (TROI) to train our NAR-IQA model. Our model is built on a contrastive learning framework that incorporates LoRA-enhanced DINOv2 embeddings and is guided by supervision from existing IQA methods. We train exclusively on synthetically generated distortions, deliberately avoiding overfitting to specific real NVS samples and thereby enhancing the model's generalization capability. Our model outperforms state-of-the-art FR-IQA, NR-IQA, and NAR-IQA methods, achieving robust performance on both aligned and non-aligned references. We also conducted a novel user study to gather data on human preferences when viewing non-aligned references in NVS. We find strong correlation between our proposed quality prediction model and the collected subjective ratings. For dataset and code, please visit our project page: https://stootaghaj.github.io/nova-project/