Related papers: COFS: Controllable Furniture layout Synthesis

Controllable person image generation aims to generate a person image conditioned on reference images, allowing precise control over the person's appearance or pose. However, prior methods often distort fine-grained textural details from the…

Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust…

Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, researchers hoping…

Recent advances in neural-based generative modeling have reignited the hopes of having computer systems capable of conversing with humans and able to understand natural language. The employment of deep neural architectures has been largely…

In this paper, we study video synthesis with emphasis on simplifying the generation conditions. Most existing video synthesis models or datasets are designed to address complex motions of a single object, lacking the ability of…

In this work, we introduce MO-SeGMan, a Multi-Objective Sequential and Guided Manipulation planner for highly constrained rearrangement problems. MO-SeGMan generates object placement sequences that minimize both replanning per object and…

Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this paper we explore the design space of Transformer models…

Learning classifier systems (LCSs) are evolutionary machine learning algorithms, flexible enough to be applied to reinforcement, supervised and unsupervised learning problems with good performance. Recently, self organizing classifiers were…

Feature coding has become increasingly important in scenarios where semantic representations rather than raw pixels are transmitted and stored. However, most existing methods are architecture-specific, targeting either CNNs or Transformers.…

Recent layout-to-image models have achieved remarkable progress in spatial controllability. However, they still struggle with inter-object occlusion. When bounding boxes overlap, most existing methods lack explicit occlusion information,…

We propose a weakly-supervised approach for conditional image generation of complex scenes where a user has fine control over objects appearing in the scene. We exploit sparse semantic maps to control object shapes and classes, as well as…

The crux of text-to-image synthesis stems from the difficulty of preserving the cross-modality semantic consistency between the input text and the synthesized image. Typical methods, which seek to model the text-to-image mapping directly,…

Deep learning methods for perception are the cornerstone of many robotic systems. Despite their potential for impressive performance, obtaining real-world training data is expensive, and can be impractically difficult for some tasks.…

The creation of complex 3D scenes tailored to user specifications has been a tedious and challenging task with traditional 3D modeling tools. Although some pioneering methods have achieved automatic text-to-3D generation, they are generally…

Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth data. Despite progress, three key limitations persist: (1)…

The significant progress on Generative Adversarial Networks (GANs) have made it possible to generate surprisingly realistic images for single object based on natural language descriptions. However, controlled generation of images for…

Sketches serve as fundamental blueprints in artistic creation because sketch editing is easier and more intuitive than pixel-level RGB image editing for painting artists, yet sketch generation remains unexplored despite advancements in…

To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis…

Despite the unprecedented success of text-to-image diffusion models, controlling the number of depicted objects using text is surprisingly hard. This is important for various applications from technical documents, to children's books to…

We are interested in learning generative models for complex geometries described via manifolds, such as spheres, tori, and other implicit surfaces. Current extensions of existing (Euclidean) generative models are restricted to specific…