paper-with-me

Papers

Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variation

2025-05-18 · Sangmin Jung, Utkarsh Nath, Yezhou Yang, Giulia Pedrielli, Joydeep Biswas, Amy Zhang, Hassan Ghasemzadeh, Pavan Turaga

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.

📄 PDF Abstract BibTeX arXiv:2505.12486

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityImage GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Guiding Vector Field Generation via Score-based Diffusion Model

2026-04-27 · Zirui Chen, Shiliang Guo, Shiyu Zhao arxiv

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 Clouds

Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation

2024-08-12 · Utkarsh Nath, Rajeev Goel, Eun Som Jeon, Changhoon Kim 외

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 3D

DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic Models

2022-12-17 · Gyeongnyeon Kim, Wooseok Jang, Gyuseong Lee, Susung Hong 외

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 Generation

Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior

2023-12-11 · CVPR 2024 1 · Fangfu Liu, Diankun Wu, Yi Wei, Yongming Rao 외

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 3D

Guiding Human-Object Interactions with Rich Geometry and Relations

2025-03-26 · CVPR 2025 1 · Mengqing Xue, Yifei Liu, Ling Guo, Shaoli Huang 외

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