Given an isolated garment image in a canonical product view and a separate image of a person, the virtual try-on task aims to generate a new image of the person wearing the target garment. Prior virtual try-on works face two major challenges in achieving this goal: a) the paired (human, garment) training data has limited availability; b) generating textures on the human that perfectly match that of the prompted garment is difficult, often resulting in distorted text and faded textures. Our work explores ways to tackle these issues through both synthetic data as well as model refinement. We introduce a garment extraction model that generates (human, synthetic garment) pairs from a single image of a clothed individual. The synthetic pairs can then be used to augment the training of virtual try-on. We also propose an Error-Aware Refinement-based Schrödinger Bridge (EARSB) that surgically targets localized generation errors for correcting the output of a base virtual try-on model. To identify likely errors, we propose a weakly-supervised error classifier that localizes regions for refinement, subsequently augmenting the Schrödinger Bridge’s noise schedule with its confidence heatmap. Experiments on VITON-HD and DressCode-Upper demonstrate that our synthetic data augmentation enhances the performance of prior work, while EARSB improves the overall image quality. In user studies, our model is preferred by the users in an average of 59% of cases. Code is available at this link.

Human image editing includes tasks like changing a person's pose, their clothing, or editing the image according to a text prompt. However, prior work often tackles these tasks separately, overlooking the benefit of mutual reinforcement from learning them jointly. In this paper, we propose UniHuman, a unified model that addresses multiple facets of human image editing in real-world settings. To enhance the model's generation quality and generalization capacity, we leverage guidance from human visual encoders and introduce a lightweight pose-warping module that can exploit different pose representations, accommodating unseen textures and patterns. Furthermore, to bridge the disparity between existing human editing benchmarks with real-world data, we curated 400K high-quality human image-text pairs for training and collected 2K human images for out-of-domain testing, both encompassing diverse clothing styles, backgrounds, and age groups. Experiments on both in-domain and out-of-domain test sets demonstrate that UniHuman outperforms task-specific models by a significant margin. In user studies, UniHuman is preferred by the users in an average of 77% of cases. Our project is available at this link.

Human pose transfer synthesizes new view(s) of a person for a given pose. Recent work achieves this via self-reconstruction, which disentangles a person’s pose and texture information by breaking the person down into parts, then recombines them for reconstruction. However, part-level disentanglement preserves some pose information that can create unwanted artifacts. In this paper, we propose Pose Transfer by Permuting Textures (PT2), an approach for self-driven human pose transfer that disentangles pose from texture at the patch-level. Specifically, we remove pose from an input image by permuting image patches so only texture information remains. Then we reconstruct the input image by sampling from the permuted textures for patch-level disentanglement. To reduce noise and recover clothing shape information from the permuted patches, we employ encoders with multiple kernel sizes in a triple branch network. Extensive experiments on DeepFashion and Market-1501 PT2reports significant gains on automatic metrics over other self-driven methods, and even outperforms some fully-supervised methods. A user study also reports images generated by our method are preferred in 68% of cases over self-driven approaches from prior work. Code is available at https://github.com/NannanLi999/pt_square

For a typical Scene Graph Generation (SGG) method in image understanding, there usually exists a large gap in the performance of the predicates’ head classes and tail classes. This phenomenon is mainly caused by the semantic overlap between different predicates as well as the long-tailed data distribution. In this paper, a Predicate Correlation Learning (PCL) method for SGG is proposed to address the above problems by taking the correlation between predicates into consideration. To measure the semantic overlap between highly correlated predicate classes, a Predicate Correlation Matrix (PCM) is defined to quantify the relationship between predicate pairs, which is dynamically updated to remove the matrix’s long-tailed bias. In addition, PCM is integrated into a predicate correlation loss function (LPC) to reduce discouraging gradients of unannotated classes. The proposed method is evaluated on several benchmarks, where the performance of the tail classes is significantly improved when built on existing methods.

Constructing adversarial examples in a black-box threat model injures the original images by introducing visual distortion. In this paper, we propose a novel black-box attack approach that can directly minimize the induced distortion by learning the noise distribution of the adversarial example, assuming only loss-oracle access to the black-box network. To quantify visual distortion, the perceptual distance between the adversarial example and the original image, is introduced in our loss. We first approximate the gradient of the corresponding non-differentiable loss function by sampling noise from the learned noise distribution. Then the distribution is updated using the estimated gradient to reduce visual distortion. The learning continues until an adversarial example is found. We validate the effectiveness of our attack on ImageNet. Our attack results in much lower distortion when compared to the state-of-the-art black-box attacks and achieves 100% success rate on InceptionV3, ResNet50 and VGG16bn. Furthermore, we theoretically prove the convergence of our model. The code is publicly available at https://github.com/Alina-1997/visual-distortion-in-attack.

Reinforcement learning (RL) has shown its advantages in image captioning by optimizing the non-differentiable metric directly in the reward learning process. However, due to the reward hacking problem in RL, maximizing reward may not lead to better quality of the caption, especially from the aspects of propositional content and distinctiveness. In this work, we propose to use a new learning method, meta learning, to utilize supervision from the ground truth whilst optimizing the reward function in RL. To improve the propositional content and the distinctiveness of the generated captions, the proposed model provides the global optimal solution by taking different gradient steps towards the supervision task and the reinforcement task, simultaneously. Experimental results on MS COCO validate the effectiveness of our approach when compared with the state-of-the-art methods.

In this paper, a novel image captioning approach is proposed to describe the content of images. Inspired by the visual processing of our cognitive system, we propose a visual-semantic LSTM model to locate the attention objects with their low-level features in the visual cell, and then successively extract high-level semantic features in the semantic cell. In addition, a state perturbation term is introduced to the word sampling strategy in the REINFORCE based method to explore proper vocabularies in the training process. Experimental results on MS COCO and Flickr30K validate the effectiveness of our approach when compared to the state-of-the-art methods.