mlsanityData to 14 Oct 2026

Towards Robust Time-of-Flight Depth Denoising with Confidence-Aware Diffusion Model

arXiv 2503.19448 ↗First posted 25 Mar 2025cs.CV eess.IVcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Time-of-Flight (ToF) sensors efficiently capture scene depth, but the nonlinear depth construction procedure often results in extremely large noise variance or even invalid areas. Recent methods based on deep neural networks (DNNs) achieve enhanced ToF denoising accuracy but tend to struggle when presented with severe noise corruption due to limited prior knowledge of ToF data distribution. In this paper, we propose DepthCAD, a novel ToF denoising approach that ensures global structural smoothness by leveraging the rich prior knowledge in Stable Diffusion and maintains local metric accuracy by steering the diffusion process with confidence guidance. To adopt the pretrained image diffusion model to ToF depth denoising, we apply the diffusion on raw ToF correlation measurements with dynamic range normalization before converting to depth maps. Experimental results validate the state-of-the-art performance of the proposed scheme, and the evaluation on real data further verifies its robustness against real-world ToF noise.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 15 of its 29 references that are in the map. First posted on arXiv 25 Mar 2025.

Builds on

15 of 29 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation4 Dec
  2. 2023Monocular Depth Estimation using Diffusion Models28 Feb

Other references · 13

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  5. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 583
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  7. 2015The Fast Bilateral Solvercited by 87
  8. 2018Tackling 3D ToF Artifacts Through Learning and the FLAT Datasetcited by 21
  9. 2019Deep Surface Normal Estimation with Hierarchical RGB-D Fusioncited by 20
  10. 2019Joint Graph-based Depth Refinement and Normal Estimationcited by 12
  11. 2018Very Power Efficient Neural Time-of-Flightcited by 8
  12. 2021RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoisingcited by 5
1 more
  1. 2021Joint Depth and Normal Estimation from Real-world Time-of-flight Raw Datacited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Digging into contrastive learning for robust depth estimation with diffusion models
  2. 2026Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration
  3. 2023DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation
  4. 2023Realistic Noise Synthesis with Diffusion Models
  5. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
  6. 2025Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model
  7. 2026Robust Depth Super-Resolution via Adaptive Diffusion Sampling
  8. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions