Most successful approaches to estimate the 6D pose of an object typically train a neural network by supervising the learning with annotated poses in real world images. These annotations are generally expensive to obtain and a common workaround is to generate and train on synthetic scenes, with the drawback of limited generalisation when the model is deployed in the real world. In this work, a two-stage 6D object pose estimator framework that can be applied on top of existing neural-network-based approaches and that does not require pose annotations on real images is proposed. The first self-supervised stage enforces the pose consistency between rendered predictions and real input images, narrowing the gap between the two domains. The second stage fine-tunes the previously trained model by enforcing the photometric consistency between pairs of different object views, where one image is warped and aligned to match the view of the other and thus enabling their comparison. In the absence of both real image annotations and depth information, applying the proposed framework on top of two recent approaches results in state-of-the-art performance when compared to methods trained only on synthetic data, domain adaptation baselines and a concurrent self-supervised approach on LINEMOD, LINEMOD OCCLUSION and HomebrewedDB datasets.
Image warping is a necessary step in many multimedia applications such as texture mapping, image-based rendering, panorama stitching, image resizing and optical flow computation etc. Traditionally, color image warping interpolation is performed in each color channel independently. In this paper, we show that the warping quality can be significantly enhanced by exploiting the cross-channel correlation. We design a warping scheme that integrates intra-channel interpolation with cross-channel variation at very low computational cost, which is required for interactive multimedia applications on mo…
Image inpainting is the task of plausibly restoring missing pixels within a hole region that is to be removed from a target image. Most existing technologies exploit patch similarities within the image, or leverage large-scale training data to fill the hole using learned semantic and texture information. However, due to the ill-posed nature of the inpainting task, such methods struggle to complete larger holes containing complicated scenes. In this paper, we propose TransFill, a multi-homography transformed fusion method to fill the hole by referring to another source image that shares scene c…
We propose a novel reference-based video colorization framework with spatiotemporal correspondence. Reference-based methods colorize grayscale frames referencing a user input color frame. Existing methods suffer from the color leakage between objects and the emergence of average colors, derived from non-local semantic correspondence in space. To address this issue, we warp colors only from the regions on the reference frame restricted by correspondence in time. We propagate masks as temporal correspondences, using two complementary tracking approaches: off-the-shelf instance tracking for high …
Single Stage Warped Cloth Learning and Semantic-Contextual Attention Feature Fusion for Virtual TryOn
Bharti School of Telecommunications, Indian Institute of Technology, Delhi, India（印度德里印度理工学院巴蒂电信学院）；Indian Institute of Information Technology, Sonepat, Haryana, India（印度哈里亚纳邦索内帕特印度信息技术学院）；Department of Electrical Engineering, Indian Institute of Technology, Delhi, India（印度德里印度理工学院电气工程系）
In this paper, we propose a numerical strategy to define a multiscale analysis for color and multicomponent images based on the representation of data on a graph. Our approach consists in computing the graph of an image using the psychovisual information and analysing it by using the spectral graph wavelet transform. We suggest introducing color dimension into the computation of the weights of the graph and using the geodesic distance as a means of distance measurement. We thus have defined a wavelet transform based on a graph with perceptual information by using the CIELab color distance. Thi…
Harbin Institute of Technology（哈尔滨工业大学）；SenseTime Research（商汤科技研究院）；Pazhou Lab（琶洲实验室）
Learning RAW-to-sRGB mapping has drawn increasing attention in recent years, wherein an input raw image is trained to imitate the target sRGB image captured by another camera. However, the severe color inconsistency makes it very challenging to generate well-aligned training pairs of input raw and target sRGB images. While learning with inaccurately aligned supervision is prone to causing pixel shift and producing blurry results. In this paper, we circumvent such issue by presenting a joint learning model for image alignment and RAW-to-sRGB mapping. To diminish the effect of color inconsistenc…
Previous virtual try-on methods usually focus on aligning a clothing item with a person, limiting their ability to exploit the complex pose, shape and skin color of the person, as well as the overall structure of the clothing, which is vital to photo-realistic virtual try-on. To address this potential weakness, we propose a fill in fabrics (FIFA) model, a self-supervised conditional generative adversarial network based framework comprised of a Fabricator and a unified virtual try-on pipeline with a Segmenter, Warper and Fuser. The Fabricator aims to reconstruct the clothing image when provided…
HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
School of Computer Science & Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University（深圳大学国家大数据系统计算技术工程实验室）；Guangdong Provincial Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）
University of Missouri-Columbia（密苏里大学哥伦比亚分校）；Instituto de Telecomunicações（电信研究所）；University of Beira Interior（贝拉内陆大学）
In this letter we propose to denoise digital color images via an improved geometric diffusion scheme. By introducing edges detected from all three color channels into the diffusion the proposed scheme avoids color smearing artifacts. Vector valued diffusion is used to control the smoothing and the geometry of color images are taken into consideration. Color edge strength function computed from different planes is introduced and it stops the diffusion spread across chromatic edges. Experimental results indicate that the scheme achieves good denoising with edge preservation when compared to othe…
Heidelberg Collaboratory for Image Processing, Heidelberg University（海德堡大学海德堡图像处理合作实验室）；Image and Pattern Analysis Group, Heidelberg University（海德堡大学图像与模式分析组）
We present a new vectorial total variation method that addresses the problem of color consistent image filtering. Our approach is inspired from the double-opponent cell representation in the human visual cortex. Existing methods of vectorial total variation regularizers have insufficient (or no) coupling between the color channels and thus may introduce color artifacts. We address this problem by introducing a novel coupling between the color channels related to a pullback-metric from the opponent space to the data (RGB color) space. Our energy is a non-convex, non-smooth higher-order vectoria…
York University（约克大学）；École de technologie supérieure (ÉTS)（高等技术学院（ÉTS））
Image style transfer aims to manipulate the appearance of a source image, or "content" image, to share similar texture and colors of a target "style" image. Ideally, the style transfer manipulation should also preserve the semantic content of the source image. A commonly used approach to assist in transferring styles is based on Gram matrix optimization. One problem of Gram matrix-based optimization is that it does not consider the correlation between colors and their styles. Specifically, certain textures or structures should be associated with specific colors. This is particularly challengin…
LatentColorization: Latent Diffusion-Based Speaker Video Colorization
SFI Centre for Research Training in Artificial Intelligence（SFI人工智能研究培训中心）；University of Galway（戈尔韦大学）；School of Computer Science（计算机科学学院）；School of Engineering（工程学院）
Using only a model that was trained to predict where people look at images, and no additional training data, we can produce a range of powerful editing effects for reducing distraction in images. Given an image and a mask specifying the region to edit, we backpropagate through a state-of-the-art saliency model to parameterize a differentiable editing operator, such that the saliency within the masked region is reduced. We demonstrate several operators, including: a recoloring operator, which learns to apply a color transform that camouflages and blends distractors into their surroundings; a wa…
Tsinghua University（清华大学）；USTC（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
This paper deals with the challenging task of synthesizing novel views for in-the-wild photographs. Existing methods have shown promising results leveraging monocular depth estimation and color inpainting with layered depth representations. However, these methods still have limited capability to handle scenes with complex 3D geometry. We propose a new method based on the multiplane image (MPI) representation. To accommodate diverse scene layouts in the wild and tackle the difficulty in producing high-dimensional MPI contents, we design a network structure that consists of two novel modules, on…
Graphics Interchange Format (GIF) is a widely used image file format. Due to the limited number of palette colors, GIF encoding often introduces color banding artifacts. Traditionally, dithering is applied to reduce color banding, but introducing dotted-pattern artifacts. To reduce artifacts and provide a better and more efficient GIF encoding, we introduce a differentiable GIF encoding pipeline, which includes three novel neural networks: PaletteNet, DitherNet, and BandingNet. Each of these three networks provides an important functionality within the GIF encoding pipeline. PaletteNet predict…
