Related papers: Improving Human Image Animation via Semantic Repre…
Supervised training a deep neural network aims to "teach" the network to mimic human visual perception that is represented by image-and-label pairs in the training data. Superpixelized (SP) images are visually perceivable to humans, but a…
Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and nearby person. To…
Person re-identification is an important task that requires learning discriminative visual features for distinguishing different person identities. Diverse auxiliary information has been utilized to improve the visual feature learning. In…
Diffusion-based video motion customization facilitates the acquisition of human motion representations from a few video samples, while achieving arbitrary subjects transfer through precise textual conditioning. Existing approaches often…
Text-based person search aims to retrieve images of a certain pedestrian by a textual description. The key challenge of this task is to eliminate the inter-modality gap and achieve the feature alignment across modalities. In this paper, we…
Presenting high-resolution (HR) human appearance is always critical for the human-centric videos. However, current imagery equipment can hardly capture HR details all the time. Existing super-resolution algorithms barely mitigate the…
We present HumanNeRF-SE, a simple yet effective method that synthesizes diverse novel pose images with simple input. Previous HumanNeRF works require a large number of optimizable parameters to fit the human images. Instead, we reload these…
Attributes are semantically meaningful characteristics whose applicability widely crosses category boundaries. They are particularly important in describing and recognizing concepts where no explicit training example is given, \textit{e.g.,…
Pose variation is one of the key factors which prevents the network from learning a robust person re-identification (Re-ID) model. To address this issue, we propose a novel person pose-guided image generation method, which is called the…
Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on.…
Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such…
Synthesizing realistic videos of humans using neural networks has been a popular alternative to the conventional graphics-based rendering pipeline due to its high efficiency. Existing works typically formulate this as an image-to-image…
Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…
The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions. A primary challenge in this task is bridging the substantial representational gap between visual and…
For a given scene, humans can easily reason for the locations and pose to place objects. Designing a computational model to reason about these affordances poses a significant challenge, mirroring the intuitive reasoning abilities of humans.…
Existing audio-driven visual dubbing methods have achieved great success. Despite this, we observe that the semantic ambiguity between spatial and temporal domains significantly degrades the synthesis stability for the dynamic faces. We…
Human pose estimation - the process of recognizing human keypoints in a given image - is one of the most important tasks in computer vision and has a wide range of applications including movement diagnostics, surveillance, or self-driving…
Semantic correspondence made tremendous progress through the recent advancements of large vision models (LVM). While these LVMs have been shown to reliably capture local semantics, the same can currently not be said for capturing global…
Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character…
Previous harmonization methods focus on adjusting one inharmonious region in an image based on an input mask. They may face problems when dealing with different perturbations on different semantic regions without available input masks. To…