Related papers: AttriStory: Fine-grained Attribute Realization for…

World models have recently gained prominence for action-conditioned visual prediction in complex environments. However, relying on only a few recent observations causes them to lose long-term context. Consequently, within a few steps, the…

We study the problem of creating high-fidelity and animatable 3D avatars from only textual descriptions. Existing text-to-avatar methods are either limited to static avatars which cannot be animated or struggle to generate animatable…

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

Text-to-image diffusion models have revolutionized image synthesis and editing, but precise control over stylistic attributes remains a challenge, often causing unintended content modifications. We propose an approach for fine-grained…

Story generation aims to produce image sequences that depict coherent narratives while maintaining subject consistency across frames. Although existing methods have excelled in producing coherent and expressive stories, they remain largely…

Multi-view generation with camera pose control and prompt-based customization are both essential elements for achieving controllable generative models. However, existing multi-view generation models do not support customization with…

Scene text editing is a challenging task that involves modifying or inserting specified texts in an image while maintaining its natural and realistic appearance. Most previous approaches to this task rely on style-transfer models that crop…

Diffusion models have achieved remarkable advancements in text-to-image generation. However, existing models still have many difficulties when faced with multiple-object compositional generation. In this paper, we propose RealCompo, a new…

Despite recent progress in diffusion models, generating realistic head portraits from novel viewpoints remains a significant challenge. Most current approaches are constrained to limited angular ranges, predominantly focusing on frontal or…

The stylization of 3D scenes is an increasingly attractive topic in 3D vision. Although image style transfer has been extensively researched with promising results, directly applying 2D style transfer methods to 3D scenes often fails to…

Generating videos for visual storytelling can be a tedious and complex process that typically requires either live-action filming or graphics animation rendering. To bypass these challenges, our key idea is to utilize the abundance of…

Storyline visualizations are an effective means to present the evolution of plots and reveal the scenic interactions among characters. However, the design of storyline visualizations is a difficult task as users need to balance between…

This paper proposes ConsistDreamer - a novel framework that lifts 2D diffusion models with 3D awareness and 3D consistency, thus enabling high-fidelity instruction-guided scene editing. To overcome the fundamental limitation of missing 3D…

Attribute-controlled text rewriting, also known as text style-transfer, has a crucial role in regulating attributes and biases of textual training data and a machine generated text. In this work we present SimpleStyle, a minimalist yet…

Dataset distillation aims to encapsulate the rich information contained in dataset into a compact distilled dataset but it faces performance degradation as the image-per-class (IPC) setting or image resolution grows larger. Recent…

Currently, large vision-language models have gained promising progress on many downstream tasks. However, they still suffer many challenges in fine-grained visual understanding tasks, such as object attribute comprehension. Besides, there…

Character Animation aims to generating character videos from still images through driving signals. Currently, diffusion models have become the mainstream in visual generation research, owing to their robust generative capabilities. However,…

In controllable generation tasks, flexibly manipulating the generated images to attain a desired appearance or structure based on a single input image cue remains a critical and longstanding challenge. Achieving this requires the effective…

Recent text-to-image diffusion models have achieved remarkable visual fidelity but often struggle with semantic alignment to complex prompts. We introduce CritiFusion, a novel inference-time framework that integrates a multimodal semantic…

Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-trained models using domain-specific text-to-image datasets.…