Related papers: Phantom-Data : Towards a General Subject-Consisten…

The continuous development of foundational models for video generation is evolving into various applications, with subject-consistent video generation still in the exploratory stage. We refer to this as Subject-to-Video, which extracts…

Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying…

Despite the promising progress in subject-driven image generation, current models often deviate from the reference identities and struggle in complex scenes with multiple subjects. To address this challenge, we introduce OpenSubject, a…

Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…

In subject-driven text-to-image generation, recent works have achieved superior performance by training the model on synthetic datasets containing numerous image pairs. Trained on these datasets, generative models can produce text-aligned…

Recent advances in generative video modeling, driven by large-scale datasets and powerful architectures, have yielded remarkable visual realism. However, emerging evidence suggests that simply scaling data and model size does not endow…

Generating a coherent sequence of images that tells a visual story, using text-to-image diffusion models, often faces the critical challenge of maintaining subject consistency across all story scenes. Existing approaches, which typically…

Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of multi-view facial references. However, simply introducing…

Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background…

Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets…

Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating…

We introduce a novel and efficient approach for text-based video-to-video editing that eliminates the need for resource-intensive per-video-per-model finetuning. At the core of our approach is a synthetic paired video dataset tailored for…

While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Further progress is constrained by the absence of datasets that address three core…

Training an object instance detector where only a few training object images are available is a challenging task. One solution is a cut-and-paste method that generates a training dataset by cutting object areas out of training images and…

Image captioning requires numerous annotated image-text pairs, resulting in substantial annotation costs. Recently, large models (e.g. diffusion models and large language models) have excelled in producing high-quality images and text. This…

Training-free consistent text-to-image generation depicting the same subjects across different images is a topic of widespread recent interest. Existing works in this direction predominantly rely on cross-frame self-attention; which…

Video generation has witnessed remarkable progress with the advent of deep generative models, particularly diffusion models. While existing methods excel in generating high-quality videos from text prompts or single images, personalized…

Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods struggle to separate camouflaged object edges due to model freezing, and (2) MLLM-based…

Transferring human motion from a source to a target person poses great potential in computer vision and graphics applications. A crucial step is to manipulate sequential future motion while retaining the appearance characteristic.Previous…

Existing Subject-to-Video Generation (S2V) methods have achieved high-fidelity and subject-consistent video generation, yet remain constrained to single-view subject references. This limitation renders the S2V task reducible to an S2I + I2V…