相关论文: PoseGen: In-Context LoRA Finetuning for Pose-Contr…

Generating long videos remains a fundamental challenge, and achieving high controllability in video inpainting and outpainting is particularly demanding. To address both of these challenges simultaneously and achieve controllable video…

We tackle the long video generation problem, i.e.~generating videos beyond the output length of video generation models. Due to the computation resource constraints, video generation models can only generate video clips that are relatively…

Generating long and consistent videos has emerged as a significant yet challenging problem. While most existing diffusion-based video generation models, derived from image generation models, demonstrate promising performance in generating…

Novel view synthesis from a single image has recently attracted a lot of attention, and it has been primarily advanced by 3D deep learning and rendering techniques. However, most work is still limited by synthesizing new views within…

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection…

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…

In recent years, data-driven techniques have greatly advanced autonomous driving systems, but the need for rare and diverse training data remains a challenge, requiring significant investment in equipment and labor. World models, which…

Location-Based Social Network (LBSN) check-in trajectory data are important for many practical applications, like POI recommendation, advertising, and pandemic intervention. However, the high collection costs and ever-increasing privacy…

Audio-driven talking-head generation has advanced rapidly with diffusion-based generative models, yet producing temporally coherent videos with fine-grained motion control remains challenging. We propose DEMO, a flow-matching generative…

Pose diversity is an inherent representative characteristic of 2D images. Due to the 3D to 2D projection mechanism, there is evident content discrepancy among distinct pose images. This is the main obstacle bothering pose transformation…

Video editing using diffusion models has achieved remarkable results in generating high-quality edits for videos. However, current methods often rely on large-scale pretraining, limiting flexibility for specific edits. First-frame-guided…

Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail…

Real-world talking faces often accompany with natural head movement. However, most existing talking face video generation methods only consider facial animation with fixed head pose. In this paper, we address this problem by proposing a…

Recent advances in diffusion models bring new vitality to visual content creation. However, current text-to-video generation models still face significant challenges such as high training costs, substantial data requirements, and…

Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been…

Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a…

Despite the significant progress that has been made in video generative models, existing state-of-the-art methods can only produce videos lasting 5-16 seconds, often labeled "long-form videos". Furthermore, videos exceeding 16 seconds…

Exo-to-Ego video generation aims to synthesize a first-person video from a synchronized third-person view and corresponding camera poses. While paired supervision is available, synchronized exo-ego data inherently introduces substantial…

Recent advancements in autonomous driving (AD) systems have highlighted the potential of world models in achieving robust and generalizable performance across both ordinary and challenging driving conditions. However, a key challenge…

Synthesis of long-term human motion skeleton sequences is essential to aid human-centric video generation with potential applications in Augmented Reality, 3D character animations, pedestrian trajectory prediction, etc. Long-term human…