In this study, we introduce a methodology for human image animation by leveraging a 3D
human parametric model within a latent diffusion framework to enhance shape alignment …

Character Animation aims to generating character videos from still images through driving
signals. Currently diffusion models have become the mainstream in visual generation …

Temporal action segmentation is crucial for understanding long-form videos. Previous works
on this task commonly adopt an iterative refinement paradigm by using multi-stage models …

Abstract Text-to-image (T2I) research has grown explosively in the past year owing to the
large-scale pre-trained diffusion models and many emerging personalization and editing …

The rapidly evolving fields of e-commerce and metaverse continue to seek innovative
approaches to enhance the consumer experience. At the same time, recent advancements …

This paper introduces a novel framework for virtual try-on, termed Wear-Any-Way. Different
from previous methods, Wear-Any-Way is a customizable solution. Besides generating high …

We present a novel approach for generating 360-degree high-quality, spatiotemporally
coherent human videos from a single image. Our framework combines the strengths of …

Appearance and pose-guided human generation is a burgeoning field that has captured
significant attention. This subject's primary objective is to transfer pose information from a …

Controllable person image synthesis aims at rendering a source image based on user-
specified changes in body pose or appearance. Prior art approaches leverage pixel-level …

Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis,
we study LDM for text-to-video generation, which is a formidable challenge due to the …