相关论文: ANYPORTAL: Zero-Shot Consistent Video Background R…

Monocular depth estimation remains challenging, as foundation models such as Depth Anything V2 (DA-V2) struggle with real-world images that are far from the training distribution. We introduce Re-Depth Anything, a test-time self-supervision…

Video inverse problems are fundamental to streaming, telepresence, and AR/VR, where high perceptual quality must coexist with tight latency constraints. Diffusion-based priors currently deliver state-of-the-art reconstructions, but existing…

In recent years, diffusion models have emerged as the most powerful approach in image synthesis. However, applying these models directly to video synthesis presents challenges, as it often leads to noticeable flickering contents. Although…

In this paper, we propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination degradation image restoration, which decouples the restoration process into adaptive illumination correction and diffusion-based…

In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning. We achieve this through constructing a style-aware encoder and a well-organized style dataset called…

Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and temporal control. We introduce a 4D-controllable video diffusion…

Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling…

Recent advancements in personalized image generation using diffusion models have been noteworthy. However, existing methods suffer from inefficiencies due to the requirement for subject-specific fine-tuning. This computationally intensive…

Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention. However, existing methods face challenges such as complex interaction and limited control capabilities. To…

Diffusion models have emerged as powerful priors for image editing tasks such as inpainting and local modification, where the objective is to generate realistic content that remains consistent with observed regions. In particular, zero-shot…

This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance. Instead of training…

Text-conditioned image editing has greatly benefitted from the advancements in Image Diffusion Models. However, extending these techniques to facial video editing introduces challenges in preserving facial identity throughout the source…

Replacing the background and simultaneously adjusting foreground objects is a challenging task in image editing. Current techniques for generating such images relies heavily on user interactions with image editing softwares, which is a…

We propose a diffusion-based framework for zero-shot image editing that unifies text-guided and reference-guided approaches without requiring fine-tuning. Our method leverages diffusion inversion and timestep-specific null-text embeddings…

Stereo matching on top-bottom equirectangular images provides an effective framework for full-surround perception, as vertically aligned epipolar lines enable the use of advanced perspective stereo architectures that are largely driven by…

Two of the main challenges of image restoration in real-world scenarios are the accurate characterization of an image prior and the precise modeling of the image degradation operator. Pre-trained diffusion models have been very successfully…

Recent advances in diffusion-based generative models have established a new paradigm for image and video relighting. However, extending these capabilities to 4D relighting remains challenging, due primarily to the scarcity of paired 4D…

Panoramic depth estimation provides a comprehensive solution for capturing complete $360^\circ$ environmental structural information, offering significant benefits for robotics and AR/VR applications. However, while extensively studied in…

Generating realistic talking faces is an interesting and long-standing topic in the field of computer vision. Although significant progress has been made, it is still challenging to generate high-quality dynamic faces with personalized…

We develop an automated video colorization framework that minimizes the flickering of colors across frames. If we apply image colorization techniques to successive frames of a video, they treat each frame as a separate colorization task.…