Related papers: simpleposter: a simple baseline for product poster…

Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these…

This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B…

Remarkable progress has been achieved in image generation with the introduction of generative models. However, precisely controlling the content in generated images remains a challenging task due to their fundamental training objective.…

Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of…

We present GigaPose, a fast, robust, and accurate method for CAD-based novel object pose estimation in RGB images. GigaPose first leverages discriminative "templates", rendered images of the CAD models, to recover the out-of-plane rotation…

Prompt engineering is still the primary way for users of generative text-to-image models to manipulate generated images in a targeted way. Based on treating the model as a continuous function and by passing gradients between the image space…

Images can be viewed as layered compositions, foreground objects over background, with potential occlusions. This layered representation enables independent editing of elements, offering greater flexibility for content creation. Despite the…

Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simultaneously…

Recent 6D pose estimation methods demonstrate notable performance but still face some practical limitations. For instance, many of them rely heavily on sensor depth, which may fail with challenging surface conditions, such as transparent or…

Layout is essential for graphic design and poster generation. Recently, applying deep learning models to generate layouts has attracted increasing attention. This paper focuses on using the GAN-based model conditioned on image contents to…

Personalized content filtering, such as recommender systems, has become a critical infrastructure to alleviate information overload. However, these systems merely filter existing content and are constrained by its limited diversity, making…

Panoptic segmentation is an important computer vision task, where the current state-of-the-art solutions require specialized components to perform well. We propose a simple generalist framework based on a deep encoder - shallow decoder…

Personalizing image generation and editing is particularly challenging when we only have a few images of the subject, or even a single image. A common approach to personalization is concept learning, which can integrate the subject into…

The emergence of diffusion models has enabled the generation of diverse high-quality images solely from text, prompting subsequent efforts to enhance the controllability of these models. Despite the improvement in controllability, pose…

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…

There has been significant progress in personalized image synthesis with methods such as Textual Inversion, DreamBooth, and LoRA. Yet, their real-world applicability is hindered by high storage demands, lengthy fine-tuning processes, and…

Texture map production is an important part of 3D modeling and determines the rendering quality. Recently, diffusion-based methods have opened a new way for texture generation. However, restricted control flexibility and limited prompt…

Portrait editing is challenging for existing techniques due to difficulties in preserving subject features like identity. In this paper, we propose a training-based method leveraging auto-generated paired data to learn desired editing while…

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…

Face inpainting requires the model to have a precise global understanding of the facial position structure. Benefiting from the powerful capabilities of deep learning backbones, recent works in face inpainting have achieved decent…