相关论文: OutDreamer: Video Outpainting with a Diffusion Tra…

Recent object detectors have achieved impressive accuracy in identifying objects seen during training. However, real-world deployment often introduces novel and unexpected objects, referred to as out-of-distribution (OOD) objects, posing…

Rendering and inverse rendering are pivotal tasks in both computer vision and graphics. The rendering equation is the core of the two tasks, as an ideal conditional distribution transfer function from intrinsic properties to RGB images.…

Portrait animation aims to generate photo-realistic videos from a single source image by reenacting the expression and pose from a driving video. While early methods relied on 3D morphable models or feature warping techniques, they often…

Video motion transfer aims to synthesize videos by generating visual content according to a text prompt while transferring the motion pattern observed in a reference video. Recent methods predominantly use the Diffusion Transformer (DiT)…

We propose a zero-shot approach for generating consistent videos of animated characters based on Text-to-Image (T2I) diffusion models. Existing Text-to-Video (T2V) methods are expensive to train and require large-scale video datasets to…

The emergence of Diffusion Transformers (DiT) has brought significant advancements to video generation, especially in text-to-video and image-to-video tasks. Although video generation is widely applied in various fields, most existing…

The video generation field has witnessed rapid improvements with the introduction of recent diffusion models. While these models have successfully enhanced appearance quality, they still face challenges in generating coherent and natural…

We introduce Tinker, a versatile framework for high-fidelity 3D editing that operates in both one-shot and few-shot regimes without any per-scene finetuning. Unlike prior techniques that demand extensive per-scene optimization to ensure…

This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motions and incoming texts. Existing methods struggle to achieve…

Image animation has seen significant progress, driven by the powerful generative capabilities of diffusion models. However, maintaining appearance consistency with static input images and mitigating abrupt motion transitions in generated…

Data scarcity continues to be a major challenge in the field of robotic manipulation. Although diffusion models provide a promising solution for generating robotic manipulation videos, existing methods largely depend on 2D trajectories,…

We present a novel approach for generating 360-degree high-quality, spatio-temporally coherent human videos from a single image. Our framework combines the strengths of diffusion transformers for capturing global correlations across…

Video inpainting, which aims to restore corrupted video content, has experienced substantial progress. Despite these advances, existing methods, whether propagating unmasked region pixels through optical flow and receptive field priors, or…

Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In…

Recent state-of-the-art image restoration methods mostly adopt latent diffusion models with U-Net backbones, yet still facing challenges in achieving high-quality restoration due to their limited capabilities. Diffusion transformers (DiTs),…

Image diffusion models, though originally developed for image generation, implicitly capture rich semantic structures that enable various recognition and localization tasks beyond synthesis. In this work, we investigate their self-attention…

Instance segmentation datasets play a crucial role in training accurate and robust computer vision models. However, obtaining accurate mask annotations to produce high-quality segmentation datasets is a costly and labor-intensive process.…

AI-generated content has attracted lots of attention recently, but photo-realistic video synthesis is still challenging. Although many attempts using GANs and autoregressive models have been made in this area, the visual quality and length…

High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…

Text-guided diffusion models have shown superior performance in image/video generation and editing. While few explorations have been performed in 3D scenarios. In this paper, we discuss three fundamental and interesting problems on this…