Related papers: EpiDiff: Enhancing Multi-View Synthesis via Locali…
Diffusion models have revolutionized the field of talking head generation, yet still face challenges in expressiveness, controllability, and stability in long-time generation. In this research, we propose an EmotiveTalk framework to address…
Generating ground-level views and coherent 3D site models from aerial-only imagery is challenging due to extreme viewpoint changes, missing intermediate observations, and large scale variations. Existing methods either refine renderings…
Embodied visual planning aims to enable manipulation tasks by imagining how a scene evolves toward a desired goal and using the imagined trajectories to guide actions. Video diffusion models, through their image-to-video generation…
Single-image novel view synthesis is a challenging and ongoing problem that aims to generate an infinite number of consistent views from a single input image. Although significant efforts have been made to advance the quality of generated…
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…
Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas…
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…
This paper presents ThinkDiff, a novel alignment paradigm that empowers text-to-image diffusion models with multimodal in-context understanding and reasoning capabilities by integrating the strengths of vision-language models (VLMs).…
Generating physically plausible human motion is crucial for applications such as character animation and virtual reality. Existing approaches often incorporate a simulator-based motion projection layer to the diffusion process to enforce…
This paper proposes Instruct 4D-to-4D that achieves 4D awareness and spatial-temporal consistency for 2D diffusion models to generate high-quality instruction-guided dynamic scene editing results. Traditional applications of 2D diffusion…
In recent years, few-shot action recognition has attracted increasing attention. It generally adopts the paradigm of meta-learning. In this field, overcoming the overlapping distribution of classes and outliers is still a challenging…
A robust face recognition model must be trained using datasets that include a large number of subjects and numerous samples per subject under varying conditions (such as pose, expression, age, noise, and occlusion). Due to ethical and…
This paper proposes ProEdit - a simple yet effective framework for high-quality 3D scene editing guided by diffusion distillation in a novel progressive manner. Inspired by the crucial observation that multi-view inconsistency in scene…
In this work, we introduce Unique3D, a novel image-to-3D framework for efficiently generating high-quality 3D meshes from single-view images, featuring state-of-the-art generation fidelity and strong generalizability. Previous methods based…
In spite of the utility of 3-D electron back-scattered diffraction (EBSD) microscopy, the data collection process can be time-consuming with serial-sectioning. Hence, it is natural to look at other modalities, such as polarized light (PL)…
Low-field to high-field MRI synthesis has emerged as a cost-effective strategy to enhance image quality under hardware and acquisition constraints, particularly in scenarios where access to high-field scanners is limited or impractical.…
Improving the quality of hyperspectral images (HSIs), such as through super-resolution, is a crucial research area. However, generative modeling for HSIs presents several challenges. Due to their high spectral dimensionality, HSIs are too…
Generating dynamic 3D object from a single-view video is challenging due to the lack of 4D labeled data. An intuitive approach is to extend previous image-to-3D pipelines by transferring off-the-shelf image generation models such as score…
Diffusion models, widely used in image generation, rely on iterative refinement to generate images from noise. Understanding this data evolution is important for model development and interpretability, yet challenging due to its…
Recent advances in generative AI have unveiled significant potential for the creation of 3D content. However, current methods either apply a pre-trained 2D diffusion model with the time-consuming score distillation sampling (SDS), or a…