Related papers: LayerD: Decomposing Raster Graphic Designs into La…
3D-aware GANs offer new capabilities for view synthesis while preserving the editing functionalities of their 2D counterparts. GAN inversion is a crucial step that seeks the latent code to reconstruct input images or videos, subsequently…
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…
We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions, or adherent raindrops, from a short sequence of images captured by a moving camera. Our method leverages motion…
Existing scene understanding systems mainly focus on recognizing the visible parts of a scene, ignoring the intact appearance of physical objects in the real-world. Concurrently, image completion has aimed to create plausible appearance for…
Radiology Report Generation (RRG) aims to produce accurate and coherent diagnostics from medical images. Although large vision language models (LVLM) improve report fluency and accuracy, they exhibit hallucinations, generating plausible yet…
Document dewarping aims to rectify deformations in photographic document images, thus improving text readability, which has attracted much attention and made great progress, but it is still challenging to preserve document structures. Given…
Diffusion models have shown great results in image generation and in image editing. However, current approaches are limited to low resolutions due to the computational cost of training diffusion models for high-resolution generation. We…
This paper considers how to separate text and/or graphics from smooth background in screen content and mixed content images and proposes an algorithm to perform this segmentation task. The proposed methods make use of the fact that the…
We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects…
Recent works have shown exciting results in unsupervised image de-rendering -- learning to decompose 3D shape, appearance, and lighting from single-image collections without explicit supervision. However, many of these assume simplistic…
Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, struggle with sequential editing: especially with maintaining…
Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances in layered image generation and decomposition synthesize or recover layered…
Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space, and a decoder maps the generated latents back to pixels. Yet the latent-to-pixel…
Graphic icons are a cornerstone of modern design workflows, yet they are often distributed as flattened single-path or compound-path graphics, where the original semantic layering is lost. This absence of semantic decomposition hinders…
As generative models expand the possibilities of visual content creation, layered image synthesis has emerged as a promising direction for controllable and creative editing. However, existing methods struggle to fully realize this…
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…
We introduce a novel framework to build a model that can learn how to segment objects from a collection of images without any human annotation. Our method builds on the observation that the location of object segments can be perturbed…
We present layered ray intersections (LaRI), a new method for unseen geometry reasoning from a single image. Unlike conventional depth estimation that is limited to the visible surface, LaRI models multiple surfaces intersected by the…
Image of a scene captured through a piece of transparent and reflective material, such as glass, is often spoiled by a superimposed layer of reflection image. While separating the reflection from a familiar object in an image is mentally…
Automatically constructing GUI groups of different granularities constitutes a critical intelligent step towards automating GUI design and implementation tasks. Specifically, in the industrial GUI-to-code process, fragmented layers may…