mlsanityData to 13 Oct 2026

PS-EIP: Robust Photometric Stereo Based on Event Interval Profile

arXiv 2503.18341 ↗First posted 24 Mar 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, the energy-efficient photometric stereo method using an event camera has been proposed to recover surface normals from events triggered by changes in logarithmic Lambertian reflections under a moving directional light source. However, EventPS treats each event interval independently, making it sensitive to noise, shadows, and non-Lambertian reflections. This paper proposes Photometric Stereo based on Event Interval Profile (PS-EIP), a robust method that recovers pixelwise surface normals from a time-series profile of event intervals. By exploiting the continuity of the profile and introducing an outlier detection method based on profile shape, our approach enhances robustness against outliers from shadows and specular reflections. Experiments using real event data from 3D-printed objects demonstrate that PS-EIP significantly improves robustness to outliers compared to EventPS's deep-learning variant, EventPS-FCN, without relying on deep learning.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 25 of its 70 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

25 of 70 references.

References · 25

  1. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 217
  2. 2019Events-to-Video: Bringing Modern Computer Vision to Event Camerascited by 192
  3. 2018Bringing a Blurry Frame Alive at High Frame-Rate with an Event Cameracited by 141
  4. 2018Event-based Moving Object Detection and Trackingcited by 126
  5. 2018Asynchronous, Photometric Feature Tracking using Events and Framescited by 118
  6. 2018Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networkscited by 97
  7. 2018PS-FCN: A Flexible Learning Framework for Photometric Stereocited by 51
  8. 2016Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularisationcited by 49
  9. 2019Self-calibrating Deep Photometric Stereo Networkscited by 47
  10. 2018CNN-PS: CNN-based Photometric Stereo for General Non-Convex Surfacescited by 45
  11. 2018Neural Inverse Rendering for General Reflectance Photometric Stereocited by 35
  12. 2020Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfacescited by 33
13 more
  1. 2023Scalable, Detailed and Mask-Free Universal Photometric Stereocited by 30
  2. 2018Realtime Time Synchronized Event-based Stereocited by 28
  3. 2022Neural Reflectance for Shape Recovery with Shadow Handlingcited by 28
  4. 2019SPLINE-Net: Sparse Photometric Stereo through Lighting Interpolation and Normal Estimation Networkscited by 24
  5. 2021ESL: Event-based Structured Lightcited by 22
  6. 2020PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networkscited by 21
  7. 2022Universal Photometric Stereo Network using Global Lighting Contextscited by 18
  8. 2022Self-calibrating Photometric Stereo by Neural Inverse Renderingcited by 17
  9. 2023Event-based Shape from Polarizationcited by 16
  10. 2015Shape and Spatially-Varying Reflectance Estimation From Virtual Exemplarscited by 15
  11. 2022PS-Transformer: Learning Sparse Photometric Stereo Network using Self-Attention Mechanismcited by 13
  12. 2022DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Imagescited by 5
  13. 2024Physics-Free Spectrally Multiplexed Photometric Stereo under Unknown Spectral Compositioncited by 4

Built on by

Not cited yet.