DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

TL;DR

The paper introduces DF3DV-1K, a large-scale dataset with clean and cluttered images for benchmarking distractor-free radiance fields, and demonstrates its utility in evaluating and improving novel view synthesis methods.

Contribution

It provides the first large-scale dataset for distractor-free radiance fields, benchmarks recent methods, and shows how to enhance them using diffusion-based 2D augmentation.

Findings

Identified the most robust distractor-free radiance field methods.

Highlighted challenging scenarios for current methods.

Achieved significant PSNR and LPIPS improvements with diffusion-based enhancement.

Abstract

Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to support comprehensive benchmarking and to facilitate progress beyond scene-specific reconstruction. However, for distractor-free radiance fields, a large-scale dataset with clean and cluttered images per scene remains lacking, limiting the development. To address this gap, we introduce DF3DV-1K, a large-scale real-world dataset comprising 1,048 scenes, each providing clean and cluttered image sets for benchmarking. In total, the dataset contains 89,924 images captured using consumer cameras to mimic casual capture, spanning 128 distractor types and 161 scene themes across indoor and outdoor environments. A curated subset of 41 scenes, DF3DV-41, is systematically designed to evaluate the robustness of distractor-free radiance field methods under challenging scenarios. Using DF3DV-1K, we benchmark nine recent distractor-free radiance field methods and 3D Gaussian Splatting, identifying the most robust methods and the most challenging scenarios. Beyond benchmarking, we demonstrate an application of DF3DV-1K by fine-tuning a diffusion-based 2D enhancer to improve radiance field methods, achieving average improvements of 0.96 dB PSNR and 0.057 LPIPS on the held-out set (e.g., DF3DV-41) and the On-the-go dataset. We hope DF3DV-1K facilitates the development of distractor-free vision and promotes progress beyond scene-specific approaches.