Copertina

Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Yang, Xu, Xiaowei, Wang, Shuai, Zhu, Chenhui, Wen, Ruxue, Li, Xubin, Ge, Tiezheng, Wang, Limin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution
di: Wang, Shuai, et al.
Pubblicazione: (2024)

DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
di: Song, Tianhui, et al.
Pubblicazione: (2025)

Accelerating Image Generation with Sub-path Linear Approximation Model
di: Xu, Chen, et al.
Pubblicazione: (2024)

Differentiable Solver Search for Fast Diffusion Sampling
di: Wang, Shuai, et al.
Pubblicazione: (2025)

Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
di: Xu, Shaodong, et al.
Pubblicazione: (2026)

PixNerd: Pixel Neural Field Diffusion
di: Wang, Shuai, et al.
Pubblicazione: (2025)

MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
di: Zhu, Chenhui, et al.
Pubblicazione: (2025)

Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion
di: Chen, Hongyu, et al.
Pubblicazione: (2024)

Improving Human Image Animation via Semantic Representation Alignment
di: Liu, Chang, et al.
Pubblicazione: (2026)

PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise
di: Meng, Qinglong, et al.
Pubblicazione: (2024)

RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidance
di: Wang, Chengrui, et al.
Pubblicazione: (2024)

TBStar-Edit: From Image Editing Pattern Shifting to Consistency Enhancement
di: Fang, Hao, et al.
Pubblicazione: (2025)

Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion
di: Liu, Haisong, et al.
Pubblicazione: (2023)

FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization
di: Tan, Shuai, et al.
Pubblicazione: (2024)

Learning Human Skill Generators at Key-Step Levels
di: Wu, Yilu, et al.
Pubblicazione: (2025)

Optical Flow Representation Alignment Mamba Diffusion Model for Medical Video Generation
di: Wang, Zhenbin, et al.
Pubblicazione: (2024)

SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
di: Zhao, Qinyu, et al.
Pubblicazione: (2025)

KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKV
di: Chen, Zhihao, et al.
Pubblicazione: (2026)

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
di: Yue, Zhengrong, et al.
Pubblicazione: (2025)

Enhancing Low-resolution Image Representation Through Normalizing Flows
di: Bao, Chenglong, et al.
Pubblicazione: (2026)

The Coupling Within: Flow Matching via Distilled Normalizing Flows
di: Berthelot, David, et al.
Pubblicazione: (2026)

VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization
di: Zhou, Yixuan, et al.
Pubblicazione: (2024)

Robust Message Embedding via Attention Flow-Based Steganography
di: Ye, Huayuan, et al.
Pubblicazione: (2024)

DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detection
di: Wu, Ruituo, et al.
Pubblicazione: (2024)

CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion
di: Lin, Jinzhou, et al.
Pubblicazione: (2025)

Fast Image Super-Resolution via Consistency Rectified Flow
di: Xu, Jiaqi, et al.
Pubblicazione: (2026)

Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning
di: Zhou, Zikun, et al.
Pubblicazione: (2025)

Normalizing Flows with Iterative Denoising
di: Chen, Tianrong, et al.
Pubblicazione: (2026)

SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
di: Ge, Xingtong, et al.
Pubblicazione: (2025)

DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
di: Xie, Chenxi, et al.
Pubblicazione: (2025)

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
di: Ji, Sihui, et al.
Pubblicazione: (2025)

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation
di: Lin, Min, et al.
Pubblicazione: (2024)

CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow
di: Maeda, Takahiro, et al.
Pubblicazione: (2025)

RefAlign: Representation Alignment for Reference-to-Video Generation
di: Wang, Lei, et al.
Pubblicazione: (2026)

MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow
di: Huang, Hanzhuo, et al.
Pubblicazione: (2025)

Low-dose CT Denoising with Language-engaged Dual-space Alignment
di: Chen, Zhihao, et al.
Pubblicazione: (2024)

UniCalib: Targetless LiDAR-Camera Calibration via Probabilistic Flow on Unified Depth Representations
di: Han, Shu, et al.
Pubblicazione: (2025)

FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
di: Wang, Zhen, et al.
Pubblicazione: (2026)

FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement
di: Gao, Wenshuo, et al.
Pubblicazione: (2025)

PixelFlow: Pixel-Space Generative Models with Flow
di: Chen, Shoufa, et al.
Pubblicazione: (2025)