- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Color Constancy in Two-Dimensional and Three-Dimensional Scenes: Effects of Viewing Methods and Surface Texture
摘要： There has been debate about how and why color constancy may be better in three-dimensional (3-D) scenes than in two-dimensional (2-D) scenes. Although some studies have shown better color constancy for 3-D conditions, the role of specific cues remains unclear. In this study, we compared color constancy for a 3-D miniature room (a real scene consisting of actual objects) and 2-D still images of that room presented on a monitor using three viewing methods: binocular viewing, monocular viewing, and head movement. We found that color constancy was better for the 3-D room; however, color constancy for the 2-D image improved when the viewing method caused the scene to be perceived more like a 3-D scene. Separate measurements of the perceptual 3-D effect of each viewing method also supported these results. An additional experiment comparing a miniature room and its image with and without texture suggested that surface texture of scene objects contributes to color constancy.
关键词： color,constancy,3-D perception,object recognition,adaptation
更新于2025-09-23 15:22:29
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Learning Illuminant Estimation from Object Recognition
摘要： In this paper we present a deep learning method to estimate the illuminant of an image. Our model is not trained with illuminant annotations, but with the objective of improving performance on an auxiliary task such as object recognition. To the best of our knowledge, this is the first example of a deep learning architecture for illuminant estimation that is trained without ground truth illuminants. We evaluate our solution on standard datasets for color constancy, and compare it with state of the art methods. Our proposal is shown to outperform most deep learning methods in a cross-dataset evaluation setup, and to present competitive results in a comparison with parametric solutions.
关键词： Illuminant estimation,deep learning,convolutional neural networks,computational color constancy,semi-supervised learning
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Colour Constancy for Image of Non-Uniformly Lit Scenes
摘要： This paper presents a colour constancy algorithm for images of scenes lit by non-uniform light sources. The proposed method determines number of colour regions within the image using a histogram-based algorithm. It then applies the K-means++ algorithm on the input image, dividing the image into its segments. The proposed algorithm computes the normalized average absolute difference (NAAD) for each segment’s coefficients and uses it as a measure to determine if the segment’s coefficients have sufficient colour variations. The initial colour constancy adjustment factors for each segment with sufficient colour variation is calculated based on the principle that the average values of colour components of the image are achromatic. The colour constancy adjustment weighting factors (CCAWF) for each pixel of image are determined by fusing the CCAWFs of the segments’ with sufficient colour variations, weighted by their normalized Euclidian distance of the pixel from the center of the segments. Experimental results were generated using both indoor and outdoor benchmark images from the scene illuminated by single or multiple illuminants. Results show that the proposed method outperforms the state of the art techniques subjectively and objectively.
关键词： multi-illuminants,fusion,k-means segmentation,colour constancy
更新于2025-09-23 15:22:29
-
Simplistic quantum operation sharing with a five-qubit genuinely entangled state
摘要： Based on local operations and classical communication, a tripartite quantum operation sharing (QOS) scheme is proposed by utilizing a genuine five-qubit entangled state as quantum channel. The present scheme has such prominent features as the arbitrariness of the concerned operation and the determinacy of sharing successfully as well as the constancy of entanglement resource. Besides, its intrinsic efficiency has come up to 10%, higher than most previous QOS schemes. More importantly, in terms of complexity, the operations which are necessary to accomplish the present QOS task as a whole are extremely simplistic. In addition, our scheme is feasible with the current experimental techniques.
关键词： Sharing quantum operation,Arbitrariness and determinacy as well as constancy,Simplistic procedure,Genuine five-qubit entangled state
更新于2025-09-23 15:19:57
-
Computational luminance constancy from naturalistic images
摘要： The human visual system supports stable percepts of object color even though the light that reflects from object surfaces varies significantly with the scene illumination. To understand the computations that support stable color perception, we study how estimating a target object’s luminous reflectance factor (LRF; a measure of the light reflected from the object under a standard illuminant) depends on variation in key properties of naturalistic scenes. Specifically, we study how variation in target object reflectance, illumination spectra, and the reflectance of background objects in a scene impact estimation of a target object’s LRF. To do this, we applied supervised statistical learning methods to the simulated excitations of human cone photoreceptors, obtained from labeled naturalistic images. The naturalistic images were rendered with computer graphics. The illumination spectra of the light sources and the reflectance spectra of the surfaces in the scene were generated using statistical models of natural spectral variation. Optimally decoding target object LRF from the responses of a small learned set of task-specific linear receptive fields that operate on a contrast representation of the cone excitations yields estimates that are within 13% of the correct LRF. Our work provides a framework for evaluating how different sources of scene variability limit performance on luminance constancy.
关键词： luminance constancy,color constancy,supervised learning
更新于2025-09-19 17:15:36
-
Spectral Adaptation Transform for Multispectral Constancy
摘要： The spectral reflectance of an object surface provides valuable information of its characteristics. Reflectance reconstruction from multispectral image data is typically based on certain assumptions. One of the common assumptions is that the same illumination is used for system calibration and image acquisition. The authors propose the concept of multispectral constancy which transforms the captured sensor data into an illuminant-independent representation, analogously to the concept of computational color constancy. They propose to transform the multispectral image data to a canonical representation through spectral adaptation transform (SAT). The performance of such a transform is tested on measured reflectance images. The authors also investigate the robustness of the transform to the inaccuracy of illuminant estimation in natural scenes. Results of reflectance reconstruction show that the proposed SAT is efficient and is robust to error in illuminant estimation.
关键词： multispectral imaging,multispectral constancy,spectral reconstruction,spectral adaptation transform,illuminant estimation
更新于2025-09-19 17:15:36
-
Can Color and Motion Information Be Used to Disentangle the Influence of Multiple Light Sources on Gloss Perception?
摘要： Previous results suggest that the glossiness of a surface is systematically underestimated when adjacent highlights from different light sources overlap to such an extent that they appear as a single, expanded highlight. Here we investigated how the availability of color- and motion-induced information, which may help to unravel such merged highlights, affects gloss constancy. We used images of computer-generated scenes where a complex 3D object made of glossy material was illuminated by three point light sources, which had varying distances to each other. The point lights were either all achromatic or they differed clearly in their color and the test object was either presented statically or rotating. The subjects had to adjust the smoothness of a match object illuminated by a single achromatic point light so that it appeared to have the same glossiness as the test object. The results show that color information contributes to gloss constancy in this situation: If it was available, the perceived glossiness remained almost invariant with changes in the degree of overlap between the highlights. This suggests that highlights of different color are processed separately. Motion information had no such effect but only led to a general increase in perceived glossiness.
关键词： color,gloss perception,motion,surfaces/materials,gloss constancy,light
更新于2025-09-11 14:15:04
-
A Smart System for Low-Light Image Enhancement with Color Constancy and Detail Manipulation in Complex Light Environments
摘要： Images are an important medium to represent meaningful information. It may be difficult for computer vision techniques and humans to extract valuable information from images with low illumination. Currently, the enhancement of low-quality images is a challenging task in the domain of image processing and computer graphics. Although there are many algorithms for image enhancement, the existing techniques often produce defective results with respect to the portions of the image with intense or normal illumination, and such techniques also inevitably degrade certain visual artifacts of the image. The model use for image enhancement must perform the following tasks: preserving details, improving contrast, color correction, and noise suppression. In this paper, we have proposed a framework based on a camera response and weighted least squares strategies. First, the image exposure is adjusted using brightness transformation to obtain the correct model for the camera response, and an illumination estimation approach is used to extract a ratio map. Then, the proposed model adjusts every pixel according to the calculated exposure map and Retinex theory. Additionally, a dehazing algorithm is used to remove haze and improve the contrast of the image. The color constancy parameters set the true color for images of low to average quality. Finally, a details enhancement approach preserves the naturalness and extracts more details to enhance the visual quality of the image. The experimental evidence and a comparison with several, recent state-of-the-art algorithms demonstrated that our designed framework is effective and can efficiently enhance low-light images.
关键词： naturalness preservation,Retinex theory,image enhancement,color constancy,camera response framework,low illumination
更新于2025-09-09 09:28:46
-
Is Suppression Just Normal Dichoptic Masking? Suprathreshold Considerations
摘要： PURPOSE. Amblyopic patients have a de?cit in visual acuity and contrast sensitivity in their amblyopic eye as well as suppression of the amblyopic eye input under binocular viewing conditions. In this study we wanted to assess the origin of the amblyopic suppression by studying the contrast perception of the amblyopic eye at suprathreshold levels under binocular and monocular viewing. METHODS. Using a suprathreshold contrast matching task in which the reference and target stimuli were presented to different eyes either simultaneously or successively, we measured interocular contrast matching in 10 controls and 11 amblyopes (mean age 35 6 15; 5 strabismics; 3 anisometropes; 3 mixed). This was then used as an index of the binocular balance across spatial frequency and compared against the contrast sensitivity ratio measured with the same stimuli. RESULTS. We observed that binocular matching becomes more imbalanced at high spatial frequency for amblyopes, compared with controls; that this imbalance did not depend in either group on whether the stimuli were presented simultaneously or successively; and that for both modes of presentation the matching balance correlates well with the interocular contrast sensitivity ratio (mean correlation coef?cient of the slopes R ? 0.7125). CONCLUSIONS. The results from our amblyopes show comparable losses of contrast perception at and above threshold under these binocular viewing conditions across a wide spatial frequency range, much stronger than that observed for our controls. This occurs under conditions in which there should be no dichoptic masking. Furthermore, the matching contrast could be well predicted by the monocular contrast sensitivity. Altogether, this suggests that amblyopic suppression cannot be explained by normal dichoptic masking but rather an attenuation of the input.
关键词： amblyopia,qCSF,suppression,contrast constancy,interocular matching
更新于2025-09-09 09:28:46
-
Tilt representation beyond the retinotopic level
摘要： We perceive a stable visual world, which enables successful interaction with our environment, despite movements of the eyes, head, and body. How are such perceptions formed? One possibility is that retino-centric visual input is transformed into representations at higher levels, such as head-, body-, or world-centered representations. We investigated this hypothesis using the tilt aftereffect in a balanced adaptation paradigm designed to isolate head-, body-, and world-centered aftereffects. Observers adapted to two oppositely tilted stimuli, each contingent on one of two different gaze, head, or body directions. We found aftereffects contingent on gaze direction, but not head or body direction. This demonstrates that adaptable tilt representations exist in a head-centric frame but not in higher reference frames. These aftereffects may be attributed to adaptation of retinotopic tilt-sensitive neurons whose responses are modulated by gaze direction (gain fields). Such neurons could support functionally head-centric tilt representations and are found as early as V1. On the basis of our results we would not expect activity in tilt-sensitive neurons to be modulated by head or body direction. The balanced adaptation paradigm is a useful tool for examining properties of the process responsible for gaze modulation of activity in visual neurons.
关键词： constancy,tilt aftereffect,adaptation,gain field
更新于2025-09-04 15:30:14