Current methods for extracting intrinsic image components, such as reflectance and shading, primarily rely on statistical priors. These methods focus mainly on simple synthetic scenes and isolated objects and struggle to perform well on challenging real-world data. To address this issue, we propose MLI-NeRF, which integrates Multiple Light information in Intrinsic-aware Neural Radiance Fields. By leveraging scene information provided by different light source positions complementing the multi-view information, we generate pseudo-label images for reflectance and shading to guide intrinsic image decomposition without the need for ground truth data. Our method introduces straightforward supervision for intrinsic component separation and ensures robustness across diverse scene types. We validate our approach on both synthetic and real-world datasets, outperforming existing state-of-the-art methods. Additionally, we demonstrate its applicability to various image editing tasks. Code and data are available at https://github.com/liulisixin/MLI-NeRF.

Single image scene relighting aims to generate a realistic new version of an input image so that it appears to be illuminated by a new target light condition. Although existing works have explored this problem from various perspectives, generating relit images under arbitrary light conditions remains highly challenging, and related datasets are scarce. Our work addresses this problem from both the dataset and methodological perspectives. We propose two new datasets: a synthetic dataset with the ground truth of intrinsic components and a real dataset collected under laboratory conditions. These datasets alleviate the scarcity of existing datasets. To incorporate physical consistency in the relighting pipeline, we establish a two-stage network based on intrinsic decomposition, giving outputs at intermediate steps, thereby introducing physical constraints. When the training set lacks ground truth for intrinsic decomposition, we introduce an unsupervised module to ensure that the intrinsic outputs are satisfactory. Our method outperforms the state-of-the-art methods in performance, as tested on both existing datasets and our newly developed datasets. Furthermore, pretraining our method or other prior methods using our synthetic dataset can enhance their performance on other datasets. Since our method can accommodate any light conditions, it is capable of producing animated results.

Intrinsic characterization of scenes is often the best way to overcome the illumination variability artifacts that complicate most computer vision problems, from 3D reconstruction to object or material recognition. This paper examines the deficiency of existing intrinsic image models to accurately account for the effects of illuminant color and sensor characteristics in the estimation of intrinsic images and presents a generic framework which incorporates insights from color constancy research to the intrinsic image decomposition problem. The proposed mathematical formulation includes information about the color of the illuminant and the effects of the camera sensors, both of which modify the observed color of the reflectance of the objects in the scene during the acquisition process. By modeling these effects, we get a "truly intrinsic" reflectance image, which we call absolute reflectance, which is invariant to changes of illuminant or camera sensors. This model allows us to represent a wide range of intrinsic image decompositions depending on the specific assumptions on the geometric properties of the scene configuration and the spectral properties of the light source and the acquisition system, thus unifying previous models in a single general framework. We demonstrate that even partial information about sensors improves significantly the estimated reflectance images, thus making our method applicable for a wide range of sensors. We validate our general intrinsic image framework experimentally with both synthetic data and natural images.

Scene decomposition into its illuminant, shading, and reflectance intrinsic images is an essential step for scene understanding. Collecting intrinsic image groundtruth data is a laborious task. The assumptions on which the ground-truth procedures are based limit their application to simple scenes with a single object taken in the absence of indirect lighting and interreflections. We investigate synthetic data for intrinsic image research since the extraction of ground truth is straightforward, and it allows for scenes in more realistic situations (e.g, multiple illuminants and interreflections). With this dataset we aim to motivate researchers to further explore intrinsic image decomposition in complex scenes.

We propose a saliency model termed SIM (saliency by induction mechanisms), which is based on a low-level spatiochromatic model that has successfully predicted chromatic induction phenomena. In so doing, we hypothesize that the low-level visual mechanisms that enhance or suppress image detail are also responsible for making some image regions more salient. Moreover, SIM adds geometrical grouplets to enhance complex low-level features such as corners, and suppress relatively simpler features such as edges. Since our model has been fitted on psychophysical chromatic induction data, it is largely nonparametric. SIM outperforms state-of-the-art methods in predicting eye fixations on two datasets and using two metrics.

State-of-the-art object detectors typically use shape information as a low level feature representation to capture the local structure of an object. This paper shows that early fusion of shape and color, as is popular in image classification, leads to a significant drop in performance for object detection. Moreover, such approaches also yields suboptimal results for object categories with varying importance of color and shape. In this paper we propose the use of color attributes as an explicit color representation for object detection. Color attributes are compact, computationally efficient, and when combined with traditional shape features provide state-of-the-art results for object detection. Our method is tested on the PASCAL VOC 2007 and 2009 datasets and results clearly show that our method improves over state-of-the-art techniques despite its simplicity. We also introduce a new dataset consisting of cartoon character images in which color plays a pivotal role. On this dataset, our approach yields a significant gain of 14% in mean AP over conventional state-of-the-art methods.

In the last years, intrinsic image decomposition has gained attention. Most of the state-of-the-art methods are based on the assumption that reflectance changes come along with strong image edges. Recently, user intervention in the recovery problem has proved to be a remarkable source of improvement. In this paper, we propose a novel approach that aims to overcome the shortcomings of pure edge-based methods by introducing strong surface descriptors, such as the color-name descriptor which introduces high-level considerations resembling top-down intervention. We also use a second surface descriptor, termed color-shade, which allows us to include physical considerations derived from the image formation model capturing gradual color surface variations. Both color cues are combined by means of a Markov Random Field. The method is quantitatively tested on the MIT ground truth dataset using different error metrics, achieving state-of-the-art performance.

Finding color representations that are stable to illuminant changes is still an open problem in computer vision. Until now, most approaches have been based on physical constraints or statistical assumptions derived from the scene, whereas very little attention has been paid to the effects that selected illuminants have on the final color image representation. The novelty of this paper is to propose perceptual constraints that are computed on the corrected images. We define the category hypothesis, which weights the set of feasible illuminants according to their ability to map the corrected image onto specific colors. Here, we choose these colors as the universal color categories related to basic linguistic terms, which have been psychophysically measured. These color categories encode natural color statistics, and their relevance across different cultures is indicated by the fact that they have received a common color name. From this category hypothesis, we propose a fast implementation that allows the sampling of a large set of illuminants. Experiments prove that our method rivals current state-of-art performance without the need for training algorithmic parameters. Additionally, the method can be used as a framework to insert top-down information from other sources, thus opening further research directions in solving for color constancy.

Many successful models for predicting attention in a scene involve three main steps: convolution with a set of filters, a center-surround mechanism and spatial pooling to construct a saliency map. However, integrating spatial information and justifying the choice of various parameter values remain open problems. In this paper we show that an efficient model of color appearance in human vision, which contains a principled selection of parameters as well as an innate spatial pooling mechanism, can be generalized to obtain a saliency model that outperforms state-of-the-art models. Scale integration is achieved by an inverse wavelet transform over the set of scale-weighted center-surround responses. The scale-weighting function (termed ECSF) has been optimized to better replicate psychophysical data on color appearance, and the appropriate sizes of the center-surround inhibition windows have been determined by training a Gaussian Mixture Model on eye-fixation data, thus avoiding ad-hoc parameter selection. Additionally, we conclude that the extension of a color appearance model to saliency estimation adds to the evidence for a common low-level visual front-end for different visual tasks.

We describe a novel technique for feature combination in the bag-of-words model of image classification. Our approach builds discriminative compound words from primitive cues learned independently from training images. Our main observation is that modeling joint-cue distributions independently is more statistically robust for typical classification problems than attempting to empirically estimate the dependent, joint-cue distribution directly. We use Information theoretic vocabulary compression to find discriminative combinations of cues and the resulting vocabulary of portmanteau words is compact, has the cue binding property, and supports individual weighting of cues in the final image representation. State-of-the-art results on both the Oxford Flower-102 and Caltech-UCSD Bird-200 datasets demonstrate the effectiveness of our technique compared to other, significantly more complex approaches to multi-cue image representation

The segmentation of a single material reflectance is a challenging problem due to the considerable variation in image measurements caused by the geometry of the object, shadows, and specularities. The combination of these effects has been modeled by the dichromatic reflection model. However, the application of the model to real-world images is limited due to unknown acquisition parameters and compression artifacts. In this paper, we present a robust model for the shape of a single material reflectance in histogram space. The method is based on a multilocal creaseness analysis of the histogram which results in a set of ridges representing the material reflectances. The segmentation method derived from these ridges is robust to both shadow, shading and specularities, and texture in real-world images. We further complete the method by incorporating prior knowledge from image statistics, and incorporate spatial coherence by using multiscale color contrast information. Results obtained show that our method clearly outperforms state-of-the-art segmentation methods on a widely used segmentation benchmark, having as a main characteristic its excellent performance in the presence of shadows and highlights at low computational cost.

Color and texture are visual cues of different nature, their integration in a useful visual descriptor is not an obvious step. One way to combine both features is to compute texture descriptors independently on each color channel. A second way is integrate the features at a descriptor level, in this case arises the problem of normalizing both cues. A significant progress in the last years in object recognition has provided the bag-of-words framework that again deals with the problem of feature combination through the definition of vocabularies of visual words. Inspired in this framework, here we present perceptual textons that will allow to fuse color and texture at the level of p-blobs, which is our feature detection step. Feature representation is based on two uniform spaces representing the attributes of the p-blobs. The low-dimensionality of these text on spaces will allow to bypass the usual problems of previous approaches. Firstly, no need for normalization between cues; and secondly, vocabularies are directly obtained from the perceptual properties of text on spaces without any learning step. Our proposal improve current state-of-art of color-texture descriptors in an image retrieval experiment over a highly diverse texture dataset from Corel.

Generally the bag-of-words based image representation follows a bottom-up paradigm. The subsequent stages of the process: feature detection, feature description, vocabulary construction and image representation are performed independent of the intentioned object classes to be detected. In such a framework, combining multiple cues such as shape and color often provides below-expected results.

In this paper we present a sharpening operator for color images that is based on perceptual considerations about how human visual behaves for color scenes. Color contrast is an induction phenomenon of the visual system that varies the chromaticity of a color region depending on the color of its surround, provoking an enhanced perception of color scenes. This effect can be simulated by a sharpening operator based on a Laplacian of Gaussian filtering combined with an interpolation process. This operator presents interesting properties to remove noise in regions of similar color, to enhance edges without destroying region structures and not prevent the creation of false color edges.

This paper proposes an improvement on a well-known colour normalisation by the introduction of some knowledge on background. Comprehensive normalisation gives an invariant representation of the image colour. This invariant representation can be considered a canonical representation whenever image content is preserved and changes are only due to illuminant conditions. One of the steps of the normalisation is based on the grey-world normalisation that removes colour changes on each channel. Because a diagonal model is assumed, the independence of chromatic variations is also achieved if the channel normalisation is applied only with background mean in spite of image mean. This will allow one to remove illuminant effects meanwhile no influence from the foreground is introduced on the normalised coordinates. It will provide an almost canonical colour space without an explicit estimation of the scene illuminant.

We present a colour segmentation method based on a normalized colour naming algorithm which removes the effects of the varying conditions due to changes in scene illuminant. Images labelled with the colour name and intensity of small regions are further processed by a region growing step providing a sound segmentation. The method has been tested on a large set of images we get from a surveillance system, whose goal is the automatic retrieval of people from an image database using their appearance description. It is given in terms of placement of the colour in clothes. Finally, a quantitative measurement to evaluate the performance of the algorithm has been defined.

This paper presents some results to decompose circular structuring elements into 3/spl times/3 elements. Decomposition allows one to improve the expended time in computing morphological operations. Generally, the shape of the structuring element determines the image transformation. Morphological operations with disks can be used as shape and size descriptors. The optimal discrete approximation of a disk can not be decomposed into 3/spl times/3 factors. Therefore, for a given radius, we give a hexadecagon that can be decomposed, and which optimally fits a disk. Afterwards, we present the decomposition of the disk in terms of the hexadecagon parameters. The decomposition prime factors can be given by different families of basic structuring elements.