Scene Analysis under Variable Illumination using Gradient Domain Methods
Explore this paper's citation graph
Summary
By analyzing the direction of intensity gradient vectors in images captured under different illumination conditions, this research presents a framework for edge suppression which avoids hard thresholds and smoothness assumptions in manipulating image gradient fields.
- Type
- dissertation
- Published
- 2006-01-01
- Cited by
- 6
- References
- 106
- OpenAlex
- https://openalex.org/W63495496
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:35867153
Keywords
Photometric stereo, Computer vision, Artificial intelligence, Outlier, Smoothness
References
- The retinex theory of color vision.
- Recovering intrinsic images from a single image
- Separation of Reflection Components Using Color and Polarization
- RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES
- Coherence-Enhancing Diffusion Filtering
- Robust ego-motion estimation and 3D model refinement using depth based parallax model
- Anisotropic diffusion in image processing
- PDE's based regularization of multivalued images and applications
- Mathematical problems in image processing - partial differential equations and the calculus of variations
- Robust incremental optical flow
- Computer Vision: A Modern Approach
- Shape and Source from Shading
- A Review of Nonlinear Diffusion Filtering
- The Bas-Relief Ambiguity
- Separation of Transparent Layers using Focus
- Depth from gradient fields and control points: bias correction in photometric stereo
- Noise Reduction in Surface Reconstruction from a Given Gradient Field
- Shape from shading using linear approximation
- Photometric method for determining surface orientation from multiple images
- A Variational Framework for Retinex
Cited by
- One-shot 3D gradient field scanning
- Wrapping-free phase retrieval with applications to interferometry, 3D-shape profiling, and deflectometry.
- Gradient domain methods with application to 4D scene reconstruction
- Poisson Image Editing
- Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems
- Gradient -domain techniques for image & video processing
Related papers
- Edge Suppression by Gradient Field Transformation Using Cross-Projection Tensors
- Directional gradients integration image for illumination insensitive face representation
- Sparse lumigraph relighting by illumination and reflectance estimation from multi-view images
- Shading-Based Surface Detail Recovery Under General Unknown Illumination
- What Object Motion Reveals about Shape with Unknown BRDF and Lighting
- Estimating parameters of an illumination model for the synthesis of specular surface textures
- Sampling reflectance functions for image-based relighting