Imagen de Portada

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Hansheng, Zhang, Kai, Tan, Hao, Guibas, Leonidas, Wetzstein, Gordon, Bi, Sai
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gaussian Mixture Flow Matching Models
por: Chen, Hansheng, et al.
Publicado: (2025)

Asymmetric Flow Models
por: Chen, Hansheng, et al.
Publicado: (2026)

Diffusion Self-Distillation for Zero-Shot Customized Image Generation
por: Cai, Shengqu, et al.
Publicado: (2024)

3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation
por: Chen, Hansheng, et al.
Publicado: (2024)

Generic 3D Diffusion Adapter Using Controlled Multi-View Editing
por: Chen, Hansheng, et al.
Publicado: (2024)

SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training
por: Zheng, Yang, et al.
Publicado: (2025)

Robust Symmetry Detection via Riemannian Langevin Dynamics
por: Je, Jihyeon, et al.
Publicado: (2024)

Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images
por: Deng, Boyang, et al.
Publicado: (2025)

Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
por: Deng, Boyang, et al.
Publicado: (2024)

Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
por: Kuang, Zhengfei, et al.
Publicado: (2024)

GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
por: Wu, Tong, et al.
Publicado: (2024)

Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors
por: Kuang, Zhengfei, et al.
Publicado: (2024)

Mode Seeking meets Mean Seeking for Fast Long Video Generation
por: Cai, Shengqu, et al.
Publicado: (2026)

4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling
por: Bahmani, Sherwin, et al.
Publicado: (2023)

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
por: Liu, Tao, et al.
Publicado: (2026)

PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers
por: Li, Songlin, et al.
Publicado: (2024)

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning
por: Chen, Guanjie, et al.
Publicado: (2025)

Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos
por: Stearns, Colton, et al.
Publicado: (2024)

Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
por: You, Yuyang, et al.
Publicado: (2026)

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
por: Dao, Quan, et al.
Publicado: (2024)

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
por: Gu, Yuchao, et al.
Publicado: (2026)

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction
por: Deng, Youming, et al.
Publicado: (2025)

Mixture of Contexts for Long Video Generation
por: Cai, Shengqu, et al.
Publicado: (2025)

Refining Pre-Trained Motion Models
por: Sun, Xinglong, et al.
Publicado: (2024)

SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
por: Luan, Wuyang, et al.
Publicado: (2026)

CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization
por: Ackermann, Jan, et al.
Publicado: (2025)

Taming Flow-based I2V Models for Creative Video Editing
por: Kong, Xianghao, et al.
Publicado: (2025)

SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling
por: Fedele, Elisabetta, et al.
Publicado: (2025)

DistillKac: Few-Step Image Generation via Damped Wave Equations
por: Han, Weiqiao, et al.
Publicado: (2025)

Flow-OPD: On-Policy Distillation for Flow Matching Models
por: Fang, Zhen, et al.
Publicado: (2026)

HumanPlus: Humanoid Shadowing and Imitation from Humans
por: Fu, Zipeng, et al.
Publicado: (2024)

Support-Set Context Matters for Bongard Problems
por: Raghuraman, Nikhil, et al.
Publicado: (2023)

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
por: Yang, Zihan, et al.
Publicado: (2026)

GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling
por: Zheng, Yang, et al.
Publicado: (2025)

FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories
por: Ke, Lei, et al.
Publicado: (2025)

View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields
por: He, Haodi, et al.
Publicado: (2024)

HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild
por: Bieri, Valentin, et al.
Publicado: (2025)

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
por: Xu, Yinghao, et al.
Publicado: (2024)

ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling
por: Zhu, William Yicheng, et al.
Publicado: (2024)

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
por: Ding, Zihan, et al.
Publicado: (2024)