Related papers: Shadow Generation with Decomposed Mask Prediction …
We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos…
Image decomposition is a crucial subject in the field of image processing. It can extract salient features from the source image. We propose a new image decomposition method based on convolutional neural network. This method can be applied…
Image foreground extraction is a classical problem in image processing and vision, with a large range of applications. In this dissertation, we focus on the extraction of text and graphics in mixed-content images, and design novel…
Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture of all objects within, is intriguing for downstream applications but remains challenging, particularly with sparse views as input. Recent approaches…
Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been…
Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. Towards this, we present 3D Compositional Zero-shot Learning…
Realistic shadow generation is a critical component for high-quality image compositing and visual effects, yet existing methods suffer from certain limitations: Physics-based approaches require a 3D scene geometry, which is often…
Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited…
We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation…
Deep learning approaches heavily rely on high-quality human supervision which is nonetheless expensive, time-consuming, and error-prone, especially for image segmentation task. In this paper, we propose a method to automatically synthesize…
Recent advancements in large generative models, particularly diffusion-based methods, have significantly enhanced the capabilities of image editing. However, achieving precise control over image composition tasks remains a challenge.…
Existing deep learning-based shadow removal methods still produce images with shadow remnants. These shadow remnants typically exist in homogeneous regions with low-intensity values, making them untraceable in the existing image-to-image…
Recent deep learning methods have achieved promising results in image shadow removal. However, their restored images still suffer from unsatisfactory boundary artifacts, due to the lack of degradation prior embedding and the deficiency in…
While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…
Learning-based lossless image compression employs pixel-based or subimage-based auto-regression for probability estimation, which achieves desirable performances. However, the existing works only consider context dependencies in one…
Compared to 2D object bounding-box labeling, it is very difficult for humans to annotate 3D object poses, especially when depth images of scenes are unavailable. This paper investigates whether we can estimate the object poses effectively…
Given a video and a set of input object masks, an omnimatte method aims to decompose the video into semantically meaningful layers containing individual objects along with their associated effects, such as shadows and reflections. Existing…
Shadows often create unwanted artifacts in photographs, and removing them can be very challenging. Previous shadow removal methods often produce de-shadowed regions that are visually inconsistent with the rest of the image. In this work we…
Previous face inverse rendering methods often require synthetic data with ground truth and/or professional equipment like a lighting stage. However, a model trained on synthetic data or using pre-defined lighting priors is typically unable…
Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under…