Cover Image

What matters for Representation Alignment: Global Information or Spatial Structure?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Singh, Jaskirat, Leng, Xingjian, Wu, Zongze, Zheng, Liang, Zhang, Richard, Shechtman, Eli, Xie, Saining
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Improved Baselines with Representation Autoencoders
by: Singh, Jaskirat, et al.
Published: (2026)

SliderSpace: Decomposing the Visual Capabilities of Diffusion Models
by: Gandikota, Rohit, et al.
Published: (2025)

End-to-End Training for Unified Tokenization and Latent Denoising
by: Duggal, Shivam, et al.
Published: (2026)

Lazy Diffusion Transformer for Interactive Image Editing
by: Nitzan, Yotam, et al.
Published: (2024)

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
by: Leng, Xingjian, et al.
Published: (2025)

Structure-Guided Image Completion with Image-level and Object-level Semantic Discriminators
by: Zheng, Haitian, et al.
Published: (2022)

VLM-Guided Adaptive Negative Prompting for Creative Generation
by: Golan, Shelly, et al.
Published: (2025)

Image Sculpting: Precise Object Editing with 3D Geometry Control
by: Yenphraphai, Jiraphon, et al.
Published: (2024)

BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing
by: Chen, Jiacheng, et al.
Published: (2025)

Distilling Diffusion Models into Conditional GANs
by: Kang, Minguk, et al.
Published: (2024)

TexSpot: 3D Texture Enhancement with Spatially-uniform Point Latent Representation
by: Lu, Ziteng, et al.
Published: (2026)

SplatFont3D: Structure-Aware Text-to-3D Artistic Font Generation with Part-Level Style Control
by: Gan, Ji, et al.
Published: (2025)

GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation
by: Hu, Sizhe, et al.
Published: (2024)

StructInbet: Integrating Explicit Structural Guidance into Inbetween Frame Generation
by: Pan, Zhenglin, et al.
Published: (2025)

AdaContour: Adaptive Contour Descriptor with Hierarchical Representation
by: Ding, Tianyu, et al.
Published: (2024)

DISK: Differentiable Sparse Kernel Complex for Efficient Spatially-Variant Convolution
by: Wu, Zhizhen, et al.
Published: (2025)

GeoFusion-CAD: Structure-Aware Diffusion with Geometric State Space for Parametric 3D Design
by: Zhou, Xiaolei, et al.
Published: (2026)

Workflow-Aware Structured Layer Decomposition for Illustration Production
by: Zhang, Tianyu, et al.
Published: (2026)

3D Gaussian Inverse Rendering with Approximated Global Illumination
by: Wu, Zirui, et al.
Published: (2025)

Negative Token Merging: Image-based Adversarial Feature Guidance
by: Singh, Jaskirat, et al.
Published: (2024)

LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model
by: Sun, Haowen, et al.
Published: (2024)

CompGS++: Compressed Gaussian Splatting for Static and Dynamic Scene Representation
by: Liu, Xiangrui, et al.
Published: (2025)

CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting
by: Liu, Xiangrui, et al.
Published: (2024)

DaReNeRF: Direction-aware Representation for Dynamic Scenes
by: Lou, Ange, et al.
Published: (2024)

A Generalizable Light Transport 3D Embedding for Global Illumination
by: Xu, Bing, et al.
Published: (2025)

Towards Geometric-Photometric Joint Alignment for Facial Mesh Registration
by: Wang, Xizhi, et al.
Published: (2024)

VLMaterial: Procedural Material Generation with Large Vision-Language Models
by: Li, Beichen, et al.
Published: (2025)

LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representation
by: Lu, Xin, et al.
Published: (2025)

Causality in Video Diffusers is Separable from Denoising
by: Bai, Xingjian, et al.
Published: (2026)

WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds
by: Li, Peizhuo, et al.
Published: (2024)

PersonaGest: Personalized Co-Speech Gesture Generation with Semantic-Guided Hierarchical Motion Representation
by: Zhao, Junchuan, et al.
Published: (2026)

TurboEdit: Instant text-based image editing
by: Wu, Zongze, et al.
Published: (2024)

DMesh: A Differentiable Mesh Representation
by: Son, Sanghyun, et al.
Published: (2024)

SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction
by: Yao, Wei, et al.
Published: (2025)

Fine-Grained Spatially Varying Material Selection in Images
by: Guerrero-Viu, Julia, et al.
Published: (2025)

Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface
by: Luo, Yihao, et al.
Published: (2025)

Limitations of (Procrustes) Alignment in Assessing Multi-Person Human Pose and Shape Estimation
by: Martin, Drazic, et al.
Published: (2024)

Text-to-Vector Generation with Neural Path Representation
by: Zhang, Peiying, et al.
Published: (2024)

MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics
by: Liu, Haofeng, et al.
Published: (2026)

Agentic 3D Scene Generation with Spatially Contextualized VLMs
by: Liu, Xinhang, et al.
Published: (2025)