{"slug": "pxdepth-pixel-space-modeling-for-structure-preserving-monocular-depth-estimation", "title": "PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation", "summary": "Researchers propose PXDepth, a monocular depth estimation model that separates global context modeling from pixel-level prediction to preserve fine-grained structures and object boundaries. The model uses a large-patch Vision Transformer for global context and Context-Modulated Pixel Transformer blocks for high-resolution spatial representations, achieving competitive zero-shot depth accuracy while maintaining efficiency. Code and models are available at the project page.", "body_md": "arXiv:2608.16984v1 Announce Type: new\nAbstract: Recent monocular depth estimators achieve strong zero-shot generalization, yet often struggle to preserve fine-grained structures and object boundaries. We attribute this limitation to the prevalent combination of large-patch ViT encoders and convolutional decoders, as coarse tokenization can weaken pixel-level cues that upsampling cannot fully recover. To address this issue, we propose PXDepth, a discriminative monocular depth model that separates global context modeling from pixel-level depth prediction. Specifically, a large-patch ViT captures global scene context, while a pixel-space predictor composed of Context-Modulated Pixel Transformer blocks maintains high-resolution spatial representations throughout depth estimation. This design preserves fine structures and sharp boundaries without sacrificing global depth consistency. Across diverse zero-shot benchmarks, PXDepth combines faithful local geometry with competitive global depth accuracy while remaining efficient at inference. Our code and model are available at https://yuanzhy29.github.io/PXDepth-Page/.", "url": "https://wpnews.pro/news/pxdepth-pixel-space-modeling-for-structure-preserving-monocular-depth-estimation", "canonical_source": "https://arxiv.org/abs/2608.16984", "published_at": "2026-08-19 04:00:00+00:00", "updated_at": "2026-08-19 04:12:37.279669+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence"], "entities": ["PXDepth", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/pxdepth-pixel-space-modeling-for-structure-preserving-monocular-depth-estimation", "markdown": "https://wpnews.pro/news/pxdepth-pixel-space-modeling-for-structure-preserving-monocular-depth-estimation.md", "text": "https://wpnews.pro/news/pxdepth-pixel-space-modeling-for-structure-preserving-monocular-depth-estimation.txt", "jsonld": "https://wpnews.pro/news/pxdepth-pixel-space-modeling-for-structure-preserving-monocular-depth-estimation.jsonld"}}