Related papers: ART: Anonymous Region Transformer for Variable Mul…
Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editing in natural language. Despite its importance, this remains…
We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers. While AR models have achieved transformative success in language modeling, replicating this…
Generating high-quality, multi-layer transparent images from text prompts can unlock a new level of creative control, allowing users to edit each layer as effortlessly as editing text outputs from LLMs. However, the development of…
Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…
Graph-structured scene descriptions can be efficiently used in generative models to control the composition of the generated image. Previous approaches are based on the combination of graph convolutional networks and adversarial methods for…
Text-driven image generation using diffusion models has recently gained significant attention. To enable more flexible image manipulation and editing, recent research has expanded from single image generation to transparent layer generation…
We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often…
We present LayerDiffuse, an approach enabling large-scale pretrained latent diffusion models to generate transparent images. The method allows generation of single transparent images or of multiple transparent layers. The method learns a…
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.…
Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the…
Deep image generation is becoming a tool to enhance artists and designers creativity potential. In this paper, we aim at making the generation process more structured and easier to interact with. Inspired by vector graphics systems, we…
Recently, how to achieve precise image editing has attracted increasing attention, especially given the remarkable success of text-to-image generation models. To unify various spatial-aware image editing abilities into one framework, we…
There has been exciting progress in generating images from natural language or layout conditions. However, these methods struggle to faithfully reproduce complex scenes due to the insufficient modeling of multiple objects and their…
Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to…
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…
Current large-scale generative models have impressive efficiency in generating high-quality images based on text prompts. However, they lack the ability to precisely control the size and position of objects in the generated image. In this…
Image matting refers to predicting the alpha values of unknown foreground areas from natural images. Prior methods have focused on propagating alpha values from known to unknown regions. However, not all natural images have a specifically…
Cutting and pasting image segments feels intuitive: the choice of source templates gives artists flexibility in recombining existing source material. Formally, this process takes an image set as input and outputs a collage of the set…
We introduce ART, Articulated Reconstruction Transformer -- a category-agnostic, feed-forward model that reconstructs complete 3D articulated objects from only sparse, multi-state RGB images. Previous methods for articulated object…
Amodal completion, generating invisible parts of occluded objects, is vital for applications like image editing and AR. Prior methods face challenges with data needs, generalization, or error accumulation in progressive pipelines. We…