Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation

• URL: http://arxiv.org/abs/2603.16340v2
• Date: Thu, 19 Mar 2026 14:04:47 GMT
• Title: Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth Estimation
• Abstract summary: textbfIris is a deterministic framework for Monocular Depth Estimation.<n>Iris generalizes strongly from synthetic to real scenes.<n>Iris achieves significant improvements in MDE with strong in-the-wild generalization.
• Score: 79.21856613345118
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose \textbf{Iris}, a deterministic framework for Monocular Depth Estimation (MDE) that integrates real-world priors into the diffusion model. Conventional feed-forward methods rely on massive training data, yet still miss details. Previous diffusion-based methods leverage rich generative priors yet struggle with synthetic-to-real domain transfer. Iris, in contrast, preserves fine details, generalizes strongly from synthetic to real scenes, and remains efficient with limited training data. To this end, we introduce a two-stage Priors-to-Geometry Deterministic (PGD) schedule: the prior stage uses Spectral-Gated Distillation (SGD) to transfer low-frequency real priors while leaving high-frequency details unconstrained, and the geometry stage applies Spectral-Gated Consistency (SGC) to enforce high-frequency fidelity while refining with synthetic ground truth. The two stages share weights and are executed with a high-to-low timestep schedule. Extensive experimental results confirm that Iris achieves significant improvements in MDE performance with strong in-the-wild generalization.

Related papers

• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Decoupled Latent Optimization of Diffusion Models for Full Waveform Inversion [4.293965179144764]
  Full waveform inversion (FWI) recovers subsurface velocity from recordings by solving a severely ill-posed, nonconstrained quadratic PDE-velocity optimization.<n>Recent diffusion-prior methods improve realism at the cost of a fragile trade-off between the standard formulation and prior consistency.<n>We propose De Latent Optimization (DLO), which relaxes the latent-penalty objective into a latent-penalty objective over an auxiliary physical variable and a latent variable.<n>On the OpenFWI benchmark, DLO outperforms classical regularizers and existing diffusion-based methods under clean, noisy, and missing-trace.
  arXiv  Detail & Related papers  (2026-06-12T05:55:10Z)
• Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting [21.300422393514804]
  We propose a deterministic framework that reformulates nowcasting as progressive frequency-decoupled refinement.<n>SDIR first extracts a stable low-frequency synoptic skeleton, then iteratively refines high-frequency textures under physical constraints.<n> Experiments on three benchmarks show SDIR significantly outperforms SOTA methods in spatial accuracy.
  arXiv  Detail & Related papers  (2026-06-01T07:34:30Z)
• Continuous-Time Distribution Matching for Few-Step Diffusion Distillation [57.28746398500951]
  We introduce Continuous-Time Distribution Matching (CDM), migrating the DMD framework from discrete anchoring to continuous optimization.<n>CDM achieves this through two continuous-time designs. First, we replace the fixed discrete schedule with a dynamic continuous schedule of random length.<n>Second, we propose a continuous-time alignment objective that performs active off-trajectory matching on latents extrapolated via the student's velocity field.
  arXiv  Detail & Related papers  (2026-05-07T14:56:39Z)
• Diffusion Models as Dataset Distillation Priors [39.4727398182562]
  We propose As Diffusion Priors (DAP), which formalizes representativeness by quantifying the similarity between synthetic and real data in feature space.<n>DAP outperforms state-of-the-art methods in generating high-fidelity datasets.<n>Our work establishes a theoretical connection between diffusion priors and the objectives of dataset distillation.
  arXiv  Detail & Related papers  (2025-10-20T11:04:09Z)
• Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency [60.74505433956616]
  continuous-time consistency model (sCM) is theoretically principled and empirically powerful for accelerating academic-scale diffusion.<n>We first develop a parallelism-compatible FlashAttention-2 JVP kernel, enabling sCM training on models with over 10 billion parameters and high-dimensional video tasks.<n>We propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer.
  arXiv  Detail & Related papers  (2025-10-09T16:45:30Z)
• Restoration Score Distillation: From Corrupted Diffusion Pretraining to One-Step High-Quality Generation [82.39763984380625]
  We propose textitRestoration Score Distillation (RSD), a principled generalization of Denoising Score Distillation (DSD)<n>RSD accommodates a broader range of corruption types, such as blurred, incomplete, or low-resolution images.<n>It consistently surpasses its teacher model across diverse restoration tasks on both natural and scientific datasets.
  arXiv  Detail & Related papers  (2025-05-19T17:21:03Z)
• Diffusion Prior Interpolation for Flexibility Real-World Face Super-Resolution [48.34173818491552]
  Diffusion Prior Interpolation (DPI) can balance consistency and diversity and can be seamlessly integrated into pre-trained models.<n>In extensive experiments conducted on synthetic and real datasets, DPI demonstrates superiority over SOTA FSR methods.
  arXiv  Detail & Related papers  (2024-12-21T09:28:44Z)
• FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation [31.06080108012735]
  We propose an efficient Monocular Depth Estimation (MDE) approach named FiffDepth.<n>FiffDepth transforms diffusion-based image generators into a feed-forward architecture for detailed depth estimation.<n>We demonstrate that FiffDepth achieves exceptional accuracy, stability, and fine-grained detail, offering significant improvements in MDE performance.
  arXiv  Detail & Related papers  (2024-12-01T04:59:34Z)
• BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation [25.047835960649167]
  BetterDepth is a conditional diffusion-based refiner that takes the prediction from pre-trained MDE models as depth conditioning. BetterDepth achieves state-of-the-art zero-shot MDE performance on diverse public datasets and on in-the-wild scenes.
  arXiv  Detail & Related papers  (2024-07-25T11:16:37Z)
• LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models [54.93010869546011]
  We propose to leverage the pre-trained latent diffusion model to perform the neural ISP for enhancing extremely low-light images.<n>Specifically, to tailor the pre-trained latent diffusion model to operate on the RAW domain, we train a set of lightweight taming modules.<n>We observe different roles of UNet denoising and decoder reconstruction in the latent diffusion model, which inspires us to decompose the low-light image enhancement task into latent-space low-frequency content generation and decoding-phase high-frequency detail maintenance.
  arXiv  Detail & Related papers  (2023-12-02T04:31:51Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)

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.