Related papers: SpotDiff: Spotting and Disentangling Interference …
Recent advances in tuning-free personalized image generation based on diffusion models are impressive. However, to improve subject fidelity, existing methods either retrain the diffusion model or infuse it with dense visual embeddings, both…
Text-to-image diffusion models have shown remarkable success in generating personalized subjects based on a few reference images. However, current methods often fail when generating multiple subjects simultaneously, resulting in mixed…
Zero-shot personalized image generation models aim to produce images that align with both a given text prompt and subject image, requiring the model to incorporate both sources of guidance. Existing methods often struggle to capture…
Group portrait editing is highly desirable since users constantly want to add a person, delete a person, or manipulate existing persons. It is also challenging due to the intricate dynamics of human interactions and the diverse gestures. In…
The burgeoning field of camouflaged object detection (COD) seeks to identify objects that blend into their surroundings. Despite the impressive performance of recent models, we have identified a limitation in their robustness, where…
Recent advances in large-scale text-to-image generation models have led to a surge in subject-driven text-to-image generation, which aims to produce customized images that align with textual descriptions while preserving the identity of…
Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…
Subject-driven image generation (SDIG) aims to manipulate specific subjects within images while adhering to textual instructions, a task crucial for advancing text-to-image diffusion models. SDIG requires reconciling the tension between…
Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such…
Benefiting from the significant advancements in text-to-image diffusion models, research in personalized image generation, particularly customized portrait generation, has also made great strides recently. However, existing methods either…
Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to control and compose the disentangled factors in the synthesis…
Occluded person re-identification (ReID) aims to match person images with occlusion. It is fundamentally challenging because of the serious occlusion which aggravates the misalignment problem between images. At the cost of incorporating a…
Small on-device models have been successfully trained with user-level differential privacy (DP) for next word prediction and image classification tasks in the past. However, existing methods can fail when directly applied to learn embedding…
Pose-guided person image generation is to transform a source person image to a target pose. This task requires spatial manipulations of source data. However, Convolutional Neural Networks are limited by the lack of ability to spatially…
Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating distinctive captions that can distinguish the target…
With the rapid advancement of 2D generative models, preserving subject identity while enabling diverse editing has emerged as a critical research focus. Existing methods typically face inherent trade-offs between identity preservation and…
Personalizing text-to-image models to generate images of specific subjects across diverse scenes and styles is a rapidly advancing field. Current approaches often face challenges in maintaining a balance between identity preservation and…
Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…
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…
Text-to-image generative models have attracted rising attention for flexible image editing via user-specified descriptions. However, text descriptions alone are not enough to elaborate the details of subjects, often compromising the…