80 results
Search Results
Now showing 1 - 10 of 80
Item ETBHD‐HMF: A Hierarchical Multimodal Fusion Architecture for Enhanced Text‐Based Hair Design(© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd., 2024) He, Rong; Jiao, Ge; Li, Chen; Alliez, Pierre; Wimmer, MichaelText‐based hair design (TBHD) represents an innovative approach that utilizes text instructions for crafting hairstyle and colour, renowned for its flexibility and scalability. However, enhancing TBHD algorithms to improve generation quality and editing accuracy remains a current research difficulty. One important reason is that existing models fall short in alignment and fusion designs. Therefore, we propose a new layered multimodal fusion network called ETBHD‐HMF, which decouples the input image and hair text information into layered hair colour and hairstyle representations. Within this network, the channel enhancement separation (CES) module is proposed to enhance important signals and suppress noise for text representation obtained from CLIP, thus improving generation quality. Based on this, we develop the weighted mapping fusion (WMF) sub‐networks for hair colour and hairstyle. This sub‐network applies the mapper operations to input image and text representations, acquiring joint information. The WMF then selectively merges image representation and joint information from various style layers using weighted operations, ultimately achieving fine‐grained hairstyle designs. Additionally, to enhance editing accuracy and quality, we design a modality alignment loss to refine and optimize the information transmission and integration of the network. The experimental results of applying the network to the CelebA‐HQ dataset demonstrate that our proposed model exhibits superior overall performance in terms of generation quality, visual realism, and editing accuracy. ETBHD‐HMF (27.8 PSNR, 0.864 IDS) outperformed HairCLIP (26.9 PSNR, 0.828 IDS), with a 3% higher PSNR and a 4% higher IDS.Item A Practical Approach to Physically-Based Reproduction of Diffusive Cosmetics(The Eurographics Association and John Wiley & Sons Ltd., 2018) Kim, Goanghun; Ko, Hyeong-Seok; Fu, Hongbo and Ghosh, Abhijeet and Kopf, JohannesIn this paper, we introduce so-called the bSX method as a new way to utilize the Kubelka-Munk (K-M) model. Assuming the material is completely diffusive, the K-M model gives the reflectance and transmittance of the material from the observation of the material applied on a backing, where the observation includes the thickness of the material application. By rearranging the original K-M equation, we propose that the reflectance and transmittance can be calculated without knowing the thickness. This is a practically useful contribution. Based on the above finding, we develop the bSX method which can (1) capture the material specific parameters from the two photos - taken before and after the material application, and (2) reproduce its effect on a novel backing. We experimented the proposed method in various cases related to virtual cosmetic try-on, which include (1) capture from a single color backing, (2) capture from human skin backing, (3) reproduction of varying thickness effect, (4) reproduction of multi-layer cosmetic application effect, (5) applying the proposed method to makeup transfer. Compared to previous image-based makeup transfer methods, the bSX method reproduces the feel of the cosmetics more accurately.Item Robust Distribution-aware Color Correction for Single-shot Images(The Eurographics Association and John Wiley & Sons Ltd., 2023) Dhillon, Daljit Singh J.; Joshi, Parisha; Baron, Jessica; Patterson, Eric K.; Chaine, Raphaëlle; Deng, Zhigang; Kim, Min H.Color correction for photographed images is an ill-posed problem. It is also a crucial initial step towards material acquisition for inverse rendering methods or pipelines. Several state-of-the-art methods rely on reducing color differences for imaged reference color chart blocks of known color values to devise or optimize their solution. In this paper, we first establish through simulations the limitation of this minimality criteria which in principle results in overfitting. Next, we study and propose a few spatial distribution measures to augment the evaluation criteria. Thereafter, we propose a novel patch-based, white-point centric approach that processes luminance and chrominance information separately to improve on the color matching task. We compare our method qualitatively with several state-of-the art methods using our augmented evaluation criteria along with quantitative examinations. Finally, we perform rigorous experiments and demonstrate results to clearly establish the benefits of our proposed method.Item High Dynamic Range Point Clouds for Real-Time Relighting(The Eurographics Association and John Wiley & Sons Ltd., 2019) Sabbadin, Manuele; Palma, Gianpaolo; BANTERLE, FRANCESCO; Boubekeur, Tamy; Cignoni, Paolo; Lee, Jehee and Theobalt, Christian and Wetzstein, GordonAcquired 3D point clouds make possible quick modeling of virtual scenes from the real world.With modern 3D capture pipelines, each point sample often comes with additional attributes such as normal vector and color response. Although rendering and processing such data has been extensively studied, little attention has been devoted using the light transport hidden in the recorded per-sample color response to relight virtual objects in visual effects (VFX) look-dev or augmented reality (AR) scenarios. Typically, standard relighting environment exploits global environment maps together with a collection of local light probes to reflect the light mood of the real scene on the virtual object. We propose instead a unified spatial approximation of the radiance and visibility relationships present in the scene, in the form of a colored point cloud. To do so, our method relies on two core components: High Dynamic Range (HDR) expansion and real-time Point-Based Global Illumination (PBGI). First, since an acquired color point cloud typically comes in Low Dynamic Range (LDR) format, we boost it using a single HDR photo exemplar of the captured scene that can cover part of it. We perform this expansion efficiently by first expanding the dynamic range of a set of renderings of the point cloud and then projecting these renderings on the original cloud. At this stage, we propagate the expansion to the regions not covered by the renderings or with low-quality dynamic range by solving a Poisson system. Then, at rendering time, we use the resulting HDR point cloud to relight virtual objects, providing a diffuse model of the indirect illumination propagated by the environment. To do so, we design a PBGI algorithm that exploits the GPU's geometry shader stage as well as a new mipmapping operator, tailored for G-buffers, to achieve real-time performances. As a result, our method can effectively relight virtual objects exhibiting diffuse and glossy physically-based materials in real time. Furthermore, it accounts for the spatial embedding of the object within the 3D environment. We evaluate our approach on manufactured scenes to assess the error introduced at every step from the perfect ground truth. We also report experiments with real captured data, covering a range of capture technologies, from active scanning to multiview stereo reconstruction.Item Rain Wiper: An Incremental RandomlyWired Network for Single Image Deraining(The Eurographics Association and John Wiley & Sons Ltd., 2019) Liang, Xiwen; Qiu, Bin; Su, Zhuo; Gao, Chengying; Shi, Xiaohong; Wang, Ruomei; Lee, Jehee and Theobalt, Christian and Wetzstein, GordonSingle image rain removal is a challenging ill-posed problem due to various shapes and densities of rain streaks. We present a novel incremental randomly wired network (IRWN) for single image deraining. Different from previous methods, most structures of modules in IRWN are generated by a stochastic network generator based on the random graph theory, which ease the burden of manual design and further help to characterize more complex rain streaks. To decrease network parameters and extract more details efficiently, the image pyramid is fused via the multi-scale network structure. An incremental rectified loss is proposed to better remove rain streaks in different rain conditions and recover the texture information of target objects. Extensive experiments on synthetic and real-world datasets demonstrate that the proposed method outperforms the state-ofthe- art methods significantly. In addition, an ablation study is conducted to illustrate the improvements obtained by different modules and loss items in IRWN.Item Adversarial Single-Image SVBRDF Estimation with Hybrid Training(The Eurographics Association and John Wiley & Sons Ltd., 2021) Zhou, Xilong; Kalantari, Nima Khademi; Mitra, Niloy and Viola, IvanIn this paper, we propose a deep learning approach for estimating the spatially-varying BRDFs (SVBRDF) from a single image. Most existing deep learning techniques use pixel-wise loss functions which limits the flexibility of the networks in handling this highly unconstrained problem. Moreover, since obtaining ground truth SVBRDF parameters is difficult, most methods typically train their networks on synthetic images and, therefore, do not effectively generalize to real examples. To avoid these limitations, we propose an adversarial framework to handle this application. Specifically, we estimate the material properties using an encoder-decoder convolutional neural network (CNN) and train it through a series of discriminators that distinguish the output of the network from ground truth. To address the gap in data distribution of synthetic and real images, we train our network on both synthetic and real examples. Specifically, we propose a strategy to train our network on pairs of real images of the same object with different lighting. We demonstrate that our approach is able to handle a variety of cases better than the state-of-the-art methods.Item Enhancing Low-Light Images: A Variation-based Retinex with Modified Bilateral Total Variation and Tensor Sparse Coding(The Eurographics Association and John Wiley & Sons Ltd., 2023) Yang, Weipeng; Gao, Hongxia; Zou, Wenbin; Huang, Shasha; Chen, Hongsheng; Ma, Jianliang; Chaine, Raphaëlle; Deng, Zhigang; Kim, Min H.Low-light conditions often result in the presence of significant noise and artifacts in captured images, which can be further exacerbated during the image enhancement process, leading to a decrease in visual quality. This paper aims to present an effective low-light image enhancement model based on the variation Retinex model that successfully suppresses noise and artifacts while preserving image details. To achieve this, we propose a modified Bilateral Total Variation to better smooth out fine textures in the illuminance component while maintaining weak structures. Additionally, tensor sparse coding is employed as a regularization term to remove noise and artifacts from the reflectance component. Experimental results on extensive and challenging datasets demonstrate the effectiveness of the proposed method, exhibiting superior or comparable performance compared to state-ofthe- art approaches. Code, dataset and experimental results are available at https://github.com/YangWeipengscut/BTRetinex.Item Neural Denoising for Deep-Z Monte Carlo Renderings(The Eurographics Association and John Wiley & Sons Ltd., 2024) Zhang, Xianyao; Röthlin, Gerhard; Zhu, Shilin; Aydin, Tunç Ozan; Salehi, Farnood; Gross, Markus; Papas, Marios; Bermano, Amit H.; Kalogerakis, EvangelosWe present a kernel-predicting neural denoising method for path-traced deep-Z images that facilitates their usage in animation and visual effects production. Deep-Z images provide enhanced flexibility during compositing as they contain color, opacity, and other rendered data at multiple depth-resolved bins within each pixel. However, they are subject to noise, and rendering until convergence is prohibitively expensive. The current state of the art in deep-Z denoising yields objectionable artifacts, and current neural denoising methods are incapable of handling the variable number of depth bins in deep-Z images. Our method extends kernel-predicting convolutional neural networks to address the challenges stemming from denoising deep-Z images. We propose a hybrid reconstruction architecture that combines the depth-resolved reconstruction at each bin with the flattened reconstruction at the pixel level. Moreover, we propose depth-aware neighbor indexing of the depth-resolved inputs to the convolution and denoising kernel application operators, which reduces artifacts caused by depth misalignment present in deep-Z images. We evaluate our method on a production-quality deep-Z dataset, demonstrating significant improvements in denoising quality and performance compared to the current state-of-the-art deep-Z denoiser. By addressing the significant challenge of the cost associated with rendering path-traced deep-Z images, we believe that our approach will pave the way for broader adoption of deep-Z workflows in future productions.Item Fast Grayscale Morphology for Circular Window(The Eurographics Association and John Wiley & Sons Ltd., 2023) Moroto, Yuji; Umetani, Nobuyuki; Chaine, Raphaëlle; Deng, Zhigang; Kim, Min H.Morphological operations are among the most popular classic image filters. The filter assumes the maximum or minimum value within a window and is often used for light object thickening and thinning operations, which are important components of various workflows, such as object recognition and stylization. Circular windows are preferred over rectangular windows for obtaining isotropic filter results. However, the existing efficient algorithms focus on rectangular or binary input images. Efficient morphological operations with circular windows for grayscale images remain challenging. In this study, we present a fast grayscale morphology heuristic computation algorithm that decomposes circular windows using the convex hull of circles. We significantly accelerate traditional methods based on Minkowski addition by introducing new decomposition rules specialized for circular windows. As our morphological operation using a convex hull can be computed independently for each pixel, the algorithm is efficient for modern multithreaded hardware.Item ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Content(The Eurographics Association and John Wiley & Sons Ltd., 2018) Marnerides, Demetris; Bashford-Rogers, Thomas; Hatchett, Jon; Debattista, Kurt; Gutierrez, Diego and Sheffer, AllaHigh dynamic range (HDR) imaging provides the capability of handling real world lighting as opposed to the traditional low dynamic range (LDR) which struggles to accurately represent images with higher dynamic range. However, most imaging content is still available only in LDR. This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet. ExpandNet accepts LDR images as input and generates images with an expanded range in an end-to-end fashion. The model attempts to reconstruct missing information that was lost from the original signal due to quantization, clipping, tone mapping or gamma correction. The added information is reconstructed from learned features, as the network is trained in a supervised fashion using a dataset of HDR images. The approach is fully automatic and data driven; it does not require any heuristics or human expertise. ExpandNet uses a multiscale architecture which avoids the use of upsampling layers to improve image quality. The method performs well compared to expansion/inverse tone mapping operators quantitatively on multiple metrics, even for badly exposed inputs.