D$^2$Turb: Depth-Aware Simulation and Decoupled Learning for Single-Frame Atmospheric Turbulence Mitigation

• URL: http://arxiv.org/abs/2605.27460v1
• Date: Mon, 25 May 2026 20:25:25 GMT
• Title: D$^2$Turb: Depth-Aware Simulation and Decoupled Learning for Single-Frame Atmospheric Turbulence Mitigation
• Abstract summary: Single-frame atmospheric turbulence mitigation is inherently ill-posed due to spatially varying blur and non-rigid geometric distortion.<n>We propose D$2$Turb, a unified framework that bridges physics-grounded simulation with explicitly decoupled restoration.<n>Building upon this simulation engine, D$2$Turb decomposes restoration into two interactive stages: texture deblurring and geometric rectification.
• Score: 17.13838108128404
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single-frame atmospheric turbulence mitigation is inherently ill-posed due to spatially varying blur coupled with non-rigid geometric distortion. Existing end-to-end approaches trained on flat-field simulations often struggle to balance texture recovery with geometric rectification. To overcome this limitation, we propose D$^2$Turb, a unified framework that bridges physics-grounded simulation with explicitly decoupled restoration. First, we introduce a Depth-Aware Turbulence Synthesis protocol that incorporates scene depth into the phase-to-space formulation. This generates physically consistent, depth-dependent degradations and provides a crucial intermediate tilt supervision signal for disentangled learning. Building upon this simulation engine, D$^2$Turb decomposes restoration into two interactive stages: texture deblurring and geometric rectification. The texture deblurring stage employs a deblurring backbone to recover fine-grained details while preserving geometric distortion for the subsequent rectification stage. To mitigate the information fragmentation commonly observed in cascaded designs, we further propose an Adaptive Structural Prior Injection (ASPI) mechanism that dynamically transfers deep structural representations from the deblurring module to guide dense flow prediction for spatial unwarping. Extensive experiments demonstrate that D$^2$Turb achieves state-of-the-art performance on both synthetic and real-world datasets, with consistent improvements in both texture recovery and geometric fidelity. Our code and pre-trained models are publicly available at https://github.com/HertzDot222/D2Turb.

Related papers

• Reliability-Aware 3D Geometric Injection for Universal Person Re-identification [47.874819213762926]
  We propose a Universal Monocular 3D-Enhanced ReID framework driven by a Consistency-Aware Reliability Gate and Dual-Stream Residual Fusion.<n>Our method improves challenging, structure-sensitive scenarios while preserving competitive performance on clean domains.
  arXiv  Detail & Related papers  (2026-07-21T08:54:25Z)
• FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity [34.142288038459704]
  FlowObject is a framework that reformulates sparse-view 3D reconstruction as a training-free, guided inverse problem.<n>Our method significantly outperforms state-of-the-art generative models and optimization-based frameworks in both geometric completeness and view-dependent appearance fidelity.
  arXiv  Detail & Related papers  (2026-06-17T12:42:09Z)
• Learning Interface Breakup: A Geometry-Conditioned Latent Surrogate for Spray Formation [16.92031035309742]
  High-fidelity volume-of-fluid (VOF) simulations with adaptive mesh refinement (AMR) are too expensive for iterative design exploration.<n>We introduce a geometry-conditioned latent surrogate trained on 797 two-phase nozzle simulations that addresses this by encoding the AMR cell-density field.<n>On held-out simulations, the method accurately captures key interface dynamics while reducing inference time to 0.045 seconds per trajectory.
  arXiv  Detail & Related papers  (2026-06-15T11:32:36Z)
• GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images [61.2170105836525]
  We propose an RGB-only framework that reformulates reconstruction as physically-grounded scene factorization and outputs a structured hybrid scene representation.<n>The resulting representation combines explicit rigid bodies with a decoupled background, enabling direct physics simulation while preserving visual realism.
  arXiv  Detail & Related papers  (2026-06-02T17:13:01Z)
• GeoRect4D: Geometry-Compatible Generative Rectification for Dynamic Sparse-View 3D Reconstruction [16.448484686109992]
  Reconstructing dynamic 3D scenes from multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating artifacts.<n>Recent attempts introduce generative priors to hallucinate missing content, yet naive integration frequently causes structural drift and temporal inconsistency.<n>We propose GeoRect4D, a novel unified framework for sparse-view dynamic reconstruction that couples explicit 3D consistency with generative refinement.
  arXiv  Detail & Related papers  (2026-04-22T17:12:02Z)
• StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation [57.06461272772509]
  StdGEN++ is a novel and comprehensive system for generating high-fidelity, semantically decomposed 3D characters from diverse inputs.<n>It achieves state-of-the-art performance, significantly outperforming existing methods in geometric accuracy and semantic disentanglement.<n>The resulting structural independence unlocks advanced downstream capabilities, including non-destructive editing, physics-compliant animation, and gaze tracking.
  arXiv  Detail & Related papers  (2026-01-12T15:41:27Z)
• UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass [83.7071371474926]
  UniSH is a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction.<n>Our framework bridges strong, disparate priors from scene reconstruction and HMR.<n>Our model achieves state-of-the-art performance on human-centric scene reconstruction.
  arXiv  Detail & Related papers  (2026-01-03T16:06:27Z)
• Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascade [38.28865883904372]
  Cascaded Sensing (Cas-Sensing) is a hierarchical reconstruction framework that integrates an autoencoder-diffusion cascade.<n>A conditional diffusion model, trained with a mask-cascade strategy, generates fine-scale details conditioned on large-scale structures.<n>Experiments on both simulation and real-world datasets demonstrate that Cas-Sensing generalizes well across varying sensor configurations and geometric boundaries.
  arXiv  Detail & Related papers  (2025-12-01T11:46:14Z)
• Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective [8.276620253870338]
  Point cloud completion aims to reconstruct complete 3D shapes from partial observations.<n>Most methods still follow a Completion-by-Inpainting paradigm.<n>We propose Completion-by-Correction, which begins with a complete shape prior and performs feature-space correction to align it with the partial observation.
  arXiv  Detail & Related papers  (2025-11-15T11:51:13Z)
• HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warping [11.035994094874141]
  HBSplat is a framework that seamlessly integrates robust structural cues, virtual view constraints, and occluded region completion.<n> HBSplat sets a new state-of-the-art, achieving up to 21.13 dB PSNR and 0.189 LPIPS, while maintaining real-time inference.
  arXiv  Detail & Related papers  (2025-09-29T15:03:31Z)
• StableGS: A Floater-Free Framework for 3D Gaussian Splatting [9.935869165752283]
  3D Gaussian Splatting (3DGS) reconstructions are plagued by stubborn floater" artifacts that degrade their geometric and visual fidelity.<n>We propose StableGS, a novel framework that decouples geometric regularization from final appearance rendering.<n> Experiments on multiple benchmarks show StableGS not only eliminates floaters but also resolves the common blur-artifact trade-off.
  arXiv  Detail & Related papers  (2025-03-24T09:02:51Z)
• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model [82.23276183684001]
  We propose a physics-inspired transformer model for imaging through atmospheric turbulence. The proposed network utilizes the power of transformer blocks to jointly extract a dynamical turbulence distortion map. We present two new real-world turbulence datasets that allow for evaluation with both classical objective metrics and a new task-driven metric using text recognition accuracy.
  arXiv  Detail & Related papers  (2022-07-20T17:09:16Z)
• Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging [142.11622043078867]
  We propose a principled Degradation-Aware Unfolding Framework (DAUF) that estimates parameters from the compressed image and physical mask, and then uses these parameters to control each iteration. By plugging HST into DAUF, we establish the first Transformer-based deep unfolding method, Degradation-Aware Unfolding Half-Shuffle Transformer (DAUHST) for HSI reconstruction.
  arXiv  Detail & Related papers  (2022-05-20T11:37:44Z)

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.