MaSS 透過學習辨識場景結構,令自監督深度估計具可擴展性
Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable
MaSS 框架透過分離結構表徵與上下文特徵,並採用場景結構判別目標,提升自監督單目深度估計在多樣場景中的可擴展性。在四個數據集上的單獨及聯合訓練與評估中,MaSS 大幅勝過以往方法,並持續受益於混合領域訓練。在另外八個數據集的零樣本評估中,MaSS 亦展現出良好的泛化能力,程式碼已公開。
Published on Oct 16
Authors:
,
,
,
,
Abstract
The MaSS framework improves self-supervised monocular depth estimation across diverse scenes by separating structural representations from contextual features and using a scene-structure discrimination objective, enabling scalable mixed-domain training and strong zero-shot generalization.
Self-supervised monocular depth estimation is appealing for its potential to scale with unlabeled data, yet existing methods often degrade when trained on diverse scenes. This study finds that, under self-supervision, models tend to encode dataset-specific structural biases rather than transferable scene geometry, leading to cross-domain optimization conflicts. To address this issue, this study proposes the MaSS framework, aiming to make self-supervised depth learning scalable to diverse data. MaSS introduces a dedicated structural representation pathway explicitly decoupled from contextual features, which is guided by a novel scene-structure discrimination objective to learn generalized, layout-aware structural representations for depth decoding. Trained and evaluated on four diverse datasets, both individually and jointly, MaSS substantially outperforms prior self-supervised methods and is the first to consistently benefit from mixed-domain training. Zero-shot evaluation on eight additional datasets further demonstrates its remarkable generalizability, particularly on those entirely out-of-distribution scenes. The source code is publicly available at https://mias.group/MaSS.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.23600
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.23600 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.23600 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.23600 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co