Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variation
Text-to-image generation models have achieved remarkable capabilities in synthesizing images, but often struggle to provide fine-grained control over the output. Existing guidance approaches, such as segmentation maps and depth maps, introduce spatial rigidity that restricts the inherent diversity of diffusion models. In this work, we introduce Deep Geometric Moments (DGM) as a novel form of guidance that encapsulates the subject's visual features and nuances through a learned geometric prior. DGMs focus specifically on the subject itself compared to DINO or CLIP features, which suffer from overemphasis on global image features or semantics. Unlike ResNets, which are sensitive to pixel-wise perturbations, DGMs rely on robust geometric moments. Our experiments demonstrate that DGM effectively balance control and diversity in diffusion-based image generation, allowing a flexible control mechanism for steering the diffusion process.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityImage GenerationText to Image GenerationText-to-Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Guiding Vector Field Generation via Score-based Diffusion Model
Guiding Vector Fields (GVFs) are a powerful tool for robotic path following. However, classical methods assume smooth, ordered curves and fail when paths are unordered, multi-branch, or generated by probabilistic models.…
Point CloudsDeep Geometric Moments Promote Shape Consistency in Text-to-3D Generation
To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines. However, the diffusion mod…
3D GenerationText to 3DDAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models
Generative models have recently undergone significant advancement due to the diffusion models. The success of these models can be often attributed to their use of guidance techniques, such as classifier or classifier-fre…
DenoisingDepth EstimationDiversityImage GenerationSherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior
Recently, 3D content creation from text prompts has demonstrated remarkable progress by utilizing 2D and 3D diffusion models. While 3D diffusion models ensure great multi-view consistency, their ability to generate high-…
3D GenerationText to 3DGuiding Human-Object Interactions with Rich Geometry and Relations
Human-object interaction (HOI) synthesis is crucial for creating immersive and realistic experiences for applications such as virtual reality. Existing methods often rely on simplified object representations, such as the…
Human-Object Interaction DetectionMotion GenerationObjectRelation