FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Chenhan, Chen, Yu, Zhang, Qingwen, Song, Jifei, Xu, Songcen, Yeung, Dit-Yan, Deng, Jiankang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914466650652672
author Jiang, Chenhan
Chen, Yu
Zhang, Qingwen
Song, Jifei
Xu, Songcen
Yeung, Dit-Yan
Deng, Jiankang
author_facet Jiang, Chenhan
Chen, Yu
Zhang, Qingwen
Song, Jifei
Xu, Songcen
Yeung, Dit-Yan
Deng, Jiankang
contents The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are typically sparse and discrete. Conversely, synthetic data scales but suffers from a domain gap and often lacks realistic semantics. We introduce FreeScale, a novel framework that leverages the power of scene reconstruction to transform limited real-world image sequences into a scalable source of high-quality training data. Our key insight is that an imperfect reconstructed scene serves as a rich geometric proxy, but naively sampling from it amplifies artifacts. To this end, we propose a certainty-aware free-view sampling strategy identifying novel viewpoints that are both semantically meaningful and minimally affected by reconstruction errors. We demonstrate FreeScale's effectiveness by scaling up the training of feedforward NVS models, achieving a notable gain of 2.7 dB in PSNR on challenging out-of-distribution benchmarks. Furthermore, we show that the generated data can actively enhance per-scene 3D Gaussian Splatting optimization, leading to consistent improvements across multiple datasets. Our work provides a practical and powerful data generation engine to overcome a fundamental bottleneck in 3D vision. Project page: https://mvp-ai-lab.github.io/FreeScale.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10512
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
Jiang, Chenhan
Chen, Yu
Zhang, Qingwen
Song, Jifei
Xu, Songcen
Yeung, Dit-Yan
Deng, Jiankang
Computer Vision and Pattern Recognition
The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are typically sparse and discrete. Conversely, synthetic data scales but suffers from a domain gap and often lacks realistic semantics. We introduce FreeScale, a novel framework that leverages the power of scene reconstruction to transform limited real-world image sequences into a scalable source of high-quality training data. Our key insight is that an imperfect reconstructed scene serves as a rich geometric proxy, but naively sampling from it amplifies artifacts. To this end, we propose a certainty-aware free-view sampling strategy identifying novel viewpoints that are both semantically meaningful and minimally affected by reconstruction errors. We demonstrate FreeScale's effectiveness by scaling up the training of feedforward NVS models, achieving a notable gain of 2.7 dB in PSNR on challenging out-of-distribution benchmarks. Furthermore, we show that the generated data can actively enhance per-scene 3D Gaussian Splatting optimization, leading to consistent improvements across multiple datasets. Our work provides a practical and powerful data generation engine to overcome a fundamental bottleneck in 3D vision. Project page: https://mvp-ai-lab.github.io/FreeScale.
title FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.10512