mlsanityData to 14 Oct 2026

Non-Learning Low-Light Stereo Vision

arXiv 2606.00379 ↗First posted 29 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a non-learning stereo framework for disparity estimation from severely noisy images. Using the Field of Junctions (FoJ), it retains coarse visual features stable under severe noise for cost volume construction while discarding fine textures inseparable from photon noise. The resulting structural information guides boundary-aware Semi-Global Matching (SGM) that dynamically adapts smoothness penalties to preserve true disparity discontinuities. The output is a sparse disparity map more accurate than those of recent stereo algorithms over unmasked pixels on widely-used benchmark datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

19 of 28 references.

References · 19

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  2. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  3. 2018Pyramid Stereo Matching Networkcited by 489
  4. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 360
  5. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 244
  6. 2019Group-wise Correlation Stereo Networkcited by 235
  7. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  8. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  9. 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matchingcited by 99
  10. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 59
  11. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 52
  12. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusioncited by 50
7 more
  1. 2025BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignmentcited by 15
  2. 2024ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Cameracited by 9
  3. 2024Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restorationcited by 9
  4. 2020Field of Junctions: Extracting Boundary Structure at Low SNRcited by 6
  5. 2025Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundariescited by 4
  6. 2024CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networkscited by 3
  7. 2024Boundary Attention: Learning curves, corners, junctions and groupingcited by 1

Built on by

Not cited yet.