This work presents AnyDoor a diffusion-based image generator with the power to teleport
target objects to new scenes at user-specified locations with desired shapes. Instead of …

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

Text-driven video generation witnesses rapid progress. However merely using text prompts
is not enough to depict the desired subject appearance that accurately aligns with users' …

With the burgeoning growth of online video platforms and the escalating volume of video
content, the demand for proficient video understanding tools has intensified markedly. Given …

Denoising diffusion models have emerged as a powerful tool for various image generation
and editing tasks, facilitating the synthesis of visual content in an unconditional or input …

Generative models can produce impressively realistic images. This paper demonstrates that
generated images have geometric features different from those of real images. We build a …

We have witnessed significant progress in deep learning-based 3D vision ranging from
neural radiance field (NeRF) based 3D representation learning to applications in novel view …

Generative object compositing emerges as a promising new avenue for compositional
image editing. However the requirement of object identity preservation poses a significant …

We present Large Language Model for Mixed Reality (LLMR), a framework for the real-time
creation and modification of interactive Mixed Reality experiences using LLMs. LLMR …

Diffusion handles is a novel approach to enable 3D object edits on diffusion images
requiring only existing pre-trained diffusion models depth estimation without any fine-tuning …