提升单目深度估计的细节保留能力，兼顾全局精度与局部清晰度。
PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation
- 用大视野ViT建模全局场景，像素空间变换器保持高分辨率细节。
- 在多个零样本测试集上实现更精细的结构还原与竞争性全局精度。
- 适合需要高保真边缘和细粒度结构的应用场景，如自动驾驶、机器人导航。
近期单目深度估计算法虽具备强零样本泛化能力，但常难以保留细粒度结构与物体边界。我们归因于主流的大块视觉变换器（ViT）编码器与卷积解码器的结合，粗粒度标记化会削弱像素级线索，而上采样无法完全恢复。为此，我们提出PXDepth，一种判别式单目深度模型，将全局上下文建模与像素级深度预测分离。具体而言，大块ViT捕捉全局场景上下文，而由上下文调制像素变换器块组成的像素空间预测器在整个深度估计过程中保持高分辨率空间表示。该设计在不牺牲全局深度一致性的情况下，有效保留了细结构与锐利边界。在多样化的零样本基准测试中，PXDepth结合了忠实的局部几何特征与具有竞争力的全局深度准确性，同时推理效率高。代码与模型已公开于 https://yuanzhy29.github.io/PXDepth-Page/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。