CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation

• URL: http://arxiv.org/abs/2604.11097v1
• Date: Mon, 13 Apr 2026 07:12:49 GMT
• Title: CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation
• Abstract summary: CDPR is a novel diffusion-based framework that integrates physically grounded polarization priors to enhance estimation robustness.<n>We show that CDPR significantly outperforms RGB-only baselines in challenging regions while maintaining competitive performance in standard scenes.
• Score: 12.658602122161989
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Monocular depth estimation is a fundamental yet challenging task in computer vision, especially under complex conditions such as textureless surfaces, transparency, and specular reflections. Recent diffusion-based approaches have significantly advanced performance by reformulating depth prediction as a denoising process in the latent space. However, existing methods rely solely on RGB inputs, which often lack sufficient cues in challenging regions. In this work, we present CDPR - Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation - a novel diffusion-based framework that integrates physically grounded polarization priors to enhance estimation robustness. Specifically, we encode both RGB and polarization (AoLP/DoLP) images into a shared latent space via a pre-trained Variational Autoencoder (VAE), and dynamically fuse multi-modal information through a learnable confidence-aware gating mechanism. This fusion module adaptively suppresses noisy signals in polarization inputs while preserving informative cues, particularly around reflective or transparent surfaces, and provides the integrated latent representation for subsequent monocular depth estimation. Beyond depth estimation, we further verify that our framework can be easily generalized to surface normal prediction with minimal modification, showcasing its scalability to general polarization-guided dense prediction tasks. Experiments on both synthetic and real-world datasets validate that CDPR significantly outperforms RGB-only baselines in challenging regions while maintaining competitive performance in standard scenes.

Related papers

• Stokes-Informed Diffusion for Robust Linear Polarization Estimation [49.459667092743445]
  GenPolar is a Stokes-informed diffusion framework grounded in the Mueller formalism from an intensity observation.<n>It achieves state-of-the-art performance in both DoLP fidelity and AoP stability.<n>These improvements translate to significant and consistent gains in downstream applications, including material detection and de-reflection.
  arXiv  Detail & Related papers  (2026-07-23T11:56:15Z)
• Conditional Polarization Guidance for Camouflaged Object Detection [5.146223292969599]
  We propose an asymmetric RGB-polarization framework to regulate RGB feature learning for camouflaged object detection.<n>Unlike conventional feature fusion strategies, the proposed conditional guidance mechanism dynamically modulates RGB features using polarization priors.<n>We also introduce a polarization edge-guided frequency refinement strategy that enhances high-frequency components under polarization constraints.
  arXiv  Detail & Related papers  (2026-03-31T17:03:06Z)
• A Single Image and Multimodality Is All You Need for Novel View Synthesis [8.273110298367644]
  We show that incorporating sparse multimodal range measurements provides a simple yet effective way to overcome limitations of diffusion-based approaches.<n>We introduce a multimodal depth reconstruction framework that leverages extremely sparse range sensing data, such as automotive radar or LiDAR.<n>Our approach models depth in an angular domain using a localized Gaussian Process formulation, enabling computationally efficient inference.
  arXiv  Detail & Related papers  (2026-02-20T00:13:11Z)
• VistaDepth: Frequency Modulation with Bias Reweighting for Enhanced Far-range Depth Estimation [13.13321690410482]
  VistaDepth is a novel framework named for its ability to accurately reconstruct far-range vistas.<n>We introduce BiasMap, a mechanism that applies adaptive weights directly to the diffusion loss in the latent space.<n>Experiments show that VistaDepth achieves state-of-the-art performance for diffusion-based MDE.
  arXiv  Detail & Related papers  (2025-04-21T13:30:51Z)
• RGB-Thermal Infrared Fusion for Robust Depth Estimation in Complex Environments [0.0]
  This paper proposes a novel multimodal depth estimation model, RTFusion, which enhances depth estimation accuracy and robustness.<n>The model incorporates a unique fusion mechanism, EGFusion, consisting of the Mutual Complementary Attention (MCA) module for cross-modal feature alignment.<n>Experiments on the MS2 and ViViD++ datasets demonstrate that the proposed model consistently produces high-quality depth maps.
  arXiv  Detail & Related papers  (2025-03-05T01:35:14Z)
• Video Frame Interpolation for Polarization via Swin-Transformer [9.10220649654041]
  Video Frame Interpolation (VFI) has been extensively explored and demonstrated, yet its application to polarization remains largely unexplored. This study proposes a multi-stage and multi-scale network called Swin-VFI based on the Swin-Transformer. Experimental results demonstrate our approach's superior reconstruction accuracy across all tasks.
  arXiv  Detail & Related papers  (2024-06-17T09:48:54Z)
• Digging into contrastive learning for robust depth estimation with diffusion models [55.62276027922499]
  We propose a novel robust depth estimation method called D4RD. It features a custom contrastive learning mode tailored for diffusion models to mitigate performance degradation in complex environments. In experiments, D4RD surpasses existing state-of-the-art solutions on synthetic corruption datasets and real-world weather conditions.
  arXiv  Detail & Related papers  (2024-04-15T14:29:47Z)
• Robust Depth Enhancement via Polarization Prompt Fusion Tuning [112.88371907047396]
  We present a framework that leverages polarization imaging to improve inaccurate depth measurements from various depth sensors. Our method first adopts a learning-based strategy where a neural network is trained to estimate a dense and complete depth map from polarization data and a sensor depth map from different sensors. To further improve the performance, we propose a Polarization Prompt Fusion Tuning (PPFT) strategy to effectively utilize RGB-based models pre-trained on large-scale datasets.
  arXiv  Detail & Related papers  (2024-04-05T17:55:33Z)
• Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios [103.72094710263656]
  This paper presents a novel approach that identifies and integrates dominant cross-modality depth features with a learning-based framework. We propose a novel confidence loss steering a confidence predictor network to yield a confidence map specifying latent potential depth areas. With the resulting confidence map, we propose a multi-modal fusion network that fuses the final depth in an end-to-end manner.
  arXiv  Detail & Related papers  (2024-02-19T04:39:16Z)
• Ternary-Type Opacity and Hybrid Odometry for RGB NeRF-SLAM [58.736472371951955]
  We introduce a ternary-type opacity (TT) model, which categorizes points on a ray intersecting a surface into three regions: before, on, and behind the surface. This enables a more accurate rendering of depth, subsequently improving the performance of image warping techniques. Our integrated approach of TT and HO achieves state-of-the-art performance on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-12-20T18:03:17Z)
• DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation [50.08080424613603]
  Long-range correlation is essential for accurate monocular depth estimation. We propose to leverage the Transformer to model this global context with an effective attention mechanism. Our proposed model, termed DepthFormer, surpasses state-of-the-art monocular depth estimation methods with prominent margins.
  arXiv  Detail & Related papers  (2022-03-27T05:03:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.