Skip to content
Preprint

FlowMoDE: Coarse-to-fine Flow Matching for Detail-aware Sim-to-Real Monocular Depth Estimation

Oct 2026 · 0 citations · 34 references
Computer Science

TL;DR

This paper presents FlowMoDE, a coarse-to-fine flow-matching-based framework for efficient, structure-aware monocular depth estimation supporting sim-to-real and cross-scene generalization and validates the generalization capability of FlowMoDE on realistic robotic scenes, with qualitative comparisons against state-of-the-art methods.

Abstract

Monocular depth estimation is a fundamental capability for 3D spatial perception in robotic and intelligent systems. While data-driven discriminative methods have achieved compelling performance for monocular depth estimation, generative approaches can reconstruct fine structural details with stronger generalization. However, most existing generative diffusion models suffer from low inference efficiency caused by multi-step sampling, whereas single-step diffusion models struggle to recover high-fidelity depth maps. To mitigate these drawbacks, this paper presents FlowMoDE, a coarse-to-fine flow-matching-based framework for efficient, structure-aware monocular depth estimation supporting sim-to-real and cross-scene generalization. The core architecture first conducts coarse-level decoding conditioned on diffused features extracted from a pre-trained semantic encoder, and subsequently restores fine-grained structural patterns via expanded decoding layers. Trained exclusively on a single synthetic indoor dataset, our proposed method outperforms prior methods across five real-world indoor and outdoor datasets, yielding an average 14.1% reduction in relative error against state-of-the-art works as well as 9.9\% reduction in chamfer distance for point cloud reconstruction. We further validate the generalization capability of FlowMoDE on realistic robotic scenes, with qualitative comparisons against state-of-the-art methods. The project page is https://flowmode-shao.netlify.app/

View source

Similar papers

Preprint Oct 2026

SAP-Depth: Scene-Adaptive Probability Framework for Self-Supervised Monocular Depth Estimation

Self-supervised monocular depth estimation remains challenging due to the loss of fine-grained details and limited adaptability to varying scene structures. In this paper, we propose SAP-Depth, a novel architecture based on Scene-Adaptive Probabilistic. Unlike traditional methods, we introduce a Dynamic Bins mechanism...

Bo-Wen He, Li Zhang, Yu-Jie Chen et al. · 0 citations
Preprint Oct 2026

EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder

Recovering detailed geometry from high-resolution images is critical for precise perception of the surroundings and objects. However, existing methods which use latent-space modeling and VAE reconstruction can compromise geometric details. Furthermore, decoding from latent codes introduces substantial inference overhea...

Bo-Wen Chai, Tian-Bao Zhang, Shu-Yu Wu et al. · 0 citations
Book Open access Nov 2026

Feature-Decoupled Lightweight Monocular Depth Estimation Trained from a Single GPU

Monocular depth estimation (MDE) predicts per-pixel depth from a single RGB image to recover the 3D structure of a scene. When trained with LiDAR supervision, MDE models can learn to predict metric-scale depth directly. However, LiDAR annotations projected onto the image plane are spatially sparse and discontinuous and...

Seung Woo Park, Do-Won Cho · 0 citations
Preprint Oct 2026

Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models

The key insight is that DA3's cross-view features, though trained only for depth consistency, implicitly encode motion-discriminative signals when combined with best-match feature search across frames, which could enable much denser temporal sampling that prior methods cannot support.

Xin-Hao Xiang, Wei-Yang Li, Zhi-Jie Zheng et al. · 0 citations
Conference Sep 2026

Environment-aware dynamic prompting for self-supervised monocular depth estimation

Self-supervised monocular depth estimation (MDE) eliminates the reliance on expensive ground-truth depth annotations and has emerged as a powerful approach for a wide range of vision applications. However, current lightweight networks are hampered by two critical challenges: the limited representation capacity of stati...

Dong-Liang Wang, Ming Jin, Xiang-Qian Fang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.