Related papers: Beyond Objects: Contextual Synthetic Data Generati…
Given a small number of images of a subject, personalized image generation techniques can fine-tune large pre-trained text-to-image diffusion models to generate images of the subject in novel contexts, conditioned on text prompts. In doing…
Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized byproduct. This imbalance compromises global scene coherence and…
One of the key shortcomings in current text-to-image (T2I) models is their inability to consistently generate images which faithfully follow the spatial relationships specified in the text prompt. In this paper, we offer a comprehensive…
Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. However, exhaustive data annotation is impracticable for each task of all domains of interest, due to high labor costs and…
Generating images from text involving complex and novel object arrangements remains a significant challenge for current text-to-image (T2I) models. Although prior layout-based methods improve object arrangements using spatial constraints…
Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…
Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…
Recent deep generative models (DGMs) such as generative adversarial networks (GANs) and diffusion probabilistic models (DPMs) have shown their impressive ability in generating high-fidelity photorealistic images. Although looking appealing…
Fine-grained image recognition is a longstanding computer vision challenge that focuses on differentiating objects belonging to multiple subordinate categories within the same meta-category. Since images belonging to the same meta-category…
Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative,…
Fine-tuning Stable Diffusion enables subject-driven image synthesis by adapting the model to generate images containing specific subjects. However, existing fine-tuning methods suffer from two key issues: underfitting, where the model fails…
Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…
Recent advances in text-to-image (T2I) diffusion models have significantly improved the quality of generated images. However, providing efficient control over individual subjects, particularly the attributes characterizing them, remains a…
Recent video generation models have revealed the emergence of Chain-of-Frame (CoF) reasoning, enabling frame-by-frame visual inference. With this capability, video models have been successfully applied to various visual tasks (e.g., maze…
Deep learning-based food image classification enables precise identification of food categories, further facilitating accurate nutritional analysis. However, real-world food images often show a skewed distribution, with some food types…
Text-to-image generation models have progressed considerably in recent years, which can now generate impressive realistic images from arbitrary text. Most of such models are trained on web-scale image-text paired datasets, which may not be…
Recently, Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated metrics have emerged to evaluate the image-text alignment capabilities of generative models. However, the performance…
Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This…
Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent works show promising results by simply fine-tuning T2I…
Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data…