相关论文: From Parts to Whole: A Unified Reference Framework…

We address the task of unsupervised retargeting of human actions from one video to another. We consider the challenging setting where only a few frames of the target is available. The core of our approach is a conditional generative model…

In recent advances of deep generative models, face reenactment -manipulating and controlling human face, including their head movement-has drawn much attention for its wide range of applicability. Despite its strong expressiveness, it is…

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.…

Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. A reoccurring challenge is how to enable a model to generate a rich variety of samples from the entire target distribution, rather…

This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components. Our method, named MaskComp, delineates the completion process through iterative…

Humans effortlessly interpret images by parsing them into part-whole hierarchies; deep learning excels in learning multi-level feature spaces, but they often lack explicit coding of part-whole relations, a prominent property of medical…

Deep generative models have been recently extended to synthesizing 3D digital humans. However, previous approaches treat clothed humans as a single chunk of geometry without considering the compositionality of clothing and accessories. As a…

Generating human portraits is a hot topic in the image generation area, e.g. mask-to-face generation and text-to-face generation. However, these unimodal generation methods lack controllability in image generation. Controllability can be…

Many of the existing Person Re-identification (Re-ID) approaches depend on feature maps which are either partitioned to localize parts of a person or reduced to create a global representation. While part localization has shown significant…

In this paper, we propose PixelHuman, a novel human rendering model that generates animatable human scenes from a few images of a person with unseen identity, views, and poses. Previous work have demonstrated reasonable performance in novel…

Text-to-motion (T2M) generation is becoming a practical tool for animation and interactive avatars. However, modifying specific body parts while maintaining overall motion coherence remains challenging. Existing methods typically rely on…

We present a deep learning approach for high resolution face completion with multiple controllable attributes (e.g., male and smiling) under arbitrary masks. Face completion entails understanding both structural meaningfulness and…

Universal medical image segmentation seeks to use a single foundational model to handle diverse tasks across multiple imaging modalities. However, existing approaches often rely heavily on manual visual prompts or retrieved reference…

General image completion and extrapolation methods often fail on portrait images where parts of the human body need to be recovered - a task that requires accurate human body structure and appearance synthesis. We present a two-stage deep…

In this paper, we address unsupervised pose-guided person image generation, which is known challenging due to non-rigid deformation. Unlike previous methods learning a rock-hard direct mapping between human bodies, we propose a new pathway…

We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the…

Recent advances in 3D generation have transitioned from multi-view 2D rendering approaches to 3D-native latent diffusion frameworks that exploit geometric priors in ground truth data. Despite progress, three key limitations persist: (1)…

Generating good quality and geometrically plausible synthetic images of humans with the ability to control appearance, pose and shape parameters, has become increasingly important for a variety of tasks ranging from photo editing, fashion…

This paper investigates a novel problem of generating images from visual attributes. We model the image as a composite of foreground and background and develop a layered generative model with disentangled latent variables that can be…

In this work, we are interested in achieving both high text controllability and whole-body appearance consistency in the generation of personalized human characters. We propose a novel framework, named SerialGen, which is a serial…