arXiv:2607. 17099v1 Announce Type: cross Abstract: Recent geometric foundation models (e.
By Feng Xue, Wu Chen, Mingshuai Zhao, Guofeng Zhong, Anlong Ming, Haozhe Wang, Dianqiao Lei, Zhaowen Lin, Haiyang Zhang, Nicu Sebe
Self-Supervised Monocular Depth Estimation (MDE) has garnered attention in recent years due to its independence from ground truth. However, most existing models are limited to a single scale and exhibit considerable performance degradation in complex driving environments.
The paper introduces FlexDepth, a family of self‑supervised monocular depth estimation models designed for robust driving perception. FlexDepth uses a two‑stage static‑dynamic decoupled training strategy and a Scale‑Driven Decoder that selects components based on scale size, enabling efficient feature fusion and high‑precision depth maps. Experiments on driving benchmarks show state‑of‑the‑art performance across arbitrary scales with minimal computational cost, with the smallest model (Flex‑Nano) achieving 37.6 FPS on mobile devices.
By Zhaowen Zhu, Li Zhang, Yujie Chen, Tian Zhang, Yingjie Wang, Mingxia Zhan
PXDepth is a monocular depth estimation model that separates global context modeling from pixel-level depth prediction. It uses a large-patch Vision Transformer to capture scene context and a pixel-space predictor with Context‑Modulated Pixel Transformer blocks to preserve high‑resolution spatial details. The approach maintains fine structures and sharp boundaries while achieving competitive global depth accuracy in zero‑shot benchmarks.
By Zhiyuan Yuan, Guanying Chen, Lingteng Qiu, Ruimao Zhang, Shuguang Cui, Xiaochun Cao
arXiv:2609.01172v1 Announce Type: new
Abstract: Monocular depth estimation has long stood as a fundamental challenge in computer vision, enabling a wide range of applications including 3D reconstruct...
By Muxin Liu, Xiaoyang Lyu, Yang-Tian Sun, Yi-Hua Huang, Ziyi Yang, Peng Dai, Xiaojuan Qi
FounRef is a training‑free method that refines frozen monocular foundation priors into dense metric depth by aligning them with sparse metric anchors. It validates anchors against the prior’s predictions, rejects misaligned ones, and applies a structure‑preserving solver to correct depth globally and locally while preserving fine geometry. The approach works out of the box on unseen cameras and scenes, achieving up to 24% lower depth error, 92% lower surface‑normal noise, and nearly 15× faster inference than a leading depth‑completion network.
By Dan Halperin, Mirko M\"ahlisch