Copertina

PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xiong, Zhexiao, Song, Yizhi, He, Liu, Xiong, Wei, Yuan, Yu, Qiao, Feng, Jacobs, Nathan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

GroundingBooth: Grounding Text-to-Image Customization
di: Xiong, Zhexiao, et al.
Pubblicazione: (2024)

Towards Open-World Generation of Stereo Images and Unsupervised Matching
di: Qiao, Feng, et al.
Pubblicazione: (2025)

GenOpticalFlow: A Generative Approach to Unsupervised Optical Flow Learning
di: Luo, Yixuan, et al.
Pubblicazione: (2026)

DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removal
di: Liu, Wanzhou, et al.
Pubblicazione: (2025)

Reconstruction Matters: Learning Geometry-Aligned BEV Representation through 3D Gaussian Splatting
di: Lu, Yiren, et al.
Pubblicazione: (2026)

PanoDreamer: Consistent Text to 360-Degree Scene Generation
di: Xiong, Zhexiao, et al.
Pubblicazione: (2025)

Mixed-View Panorama Synthesis using Geospatially Guided Diffusion
di: Xiong, Zhexiao, et al.
Pubblicazione: (2024)

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment
di: Song, Yizhi, et al.
Pubblicazione: (2024)

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

UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving
di: Xiong, Zhexiao, et al.
Pubblicazione: (2026)

PSM: Learning Probabilistic Embeddings for Multi-scale Zero-Shot Soundscape Mapping
di: Khanal, Subash, et al.
Pubblicazione: (2024)

Accelerating 4D Hyperspectral Imaging through Physics-Informed Neural Representation and Adaptive Sampling
di: Ho, Chi-Jui, et al.
Pubblicazione: (2026)

StereoGenBench: A Synthetic Multi-Camera Benchmark for Stereo Generation under Controlled Baseline Regimes
di: Cui, Yangzhi, et al.
Pubblicazione: (2026)

PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
di: Zhang, Tianyuan, et al.
Pubblicazione: (2024)

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
di: Wang, Chen, et al.
Pubblicazione: (2025)

ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
di: Chen, Yuzhi, et al.
Pubblicazione: (2026)

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
di: Ji, Sihui, et al.
Pubblicazione: (2025)

MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models
di: Hua, Hang, et al.
Pubblicazione: (2025)

PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation
di: Liu, Shaowei, et al.
Pubblicazione: (2024)

The Quadratic Geometry of Flow Matching: Semantic Granularity Alignment for Text-to-Image Synthesis
di: Xiong, Zhinan, et al.
Pubblicazione: (2026)

Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation
di: Zhang, Wenchao, et al.
Pubblicazione: (2025)

BBScoreV2: Learning Time-Evolution and Latent Alignment from Stochastic Representation
di: Zhang, Tianhao, et al.
Pubblicazione: (2024)

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation
di: Song, Yizhi, et al.
Pubblicazione: (2024)

Enhanced Partially Relevant Video Retrieval through Inter- and Intra-Sample Analysis with Coherence Prediction
di: Ren, Junlong, et al.
Pubblicazione: (2025)

Geo-Align: Video Generation Alignment via Metric Geometry Reward
di: Li, Zizun, et al.
Pubblicazione: (2026)

PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance
di: Satish, Siddarth Nilol Kundur, et al.
Pubblicazione: (2026)

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment
di: Bu, Mengyu, et al.
Pubblicazione: (2025)

GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection
di: Song, Ziying, et al.
Pubblicazione: (2023)

MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
di: Bhowmik, Aritra, et al.
Pubblicazione: (2025)

FormalAlign: Automated Alignment Evaluation for Autoformalization
di: Lu, Jianqiao, et al.
Pubblicazione: (2024)

PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
di: Xie, Tianyi, et al.
Pubblicazione: (2023)

VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
di: Zhang, Xiangdong, et al.
Pubblicazione: (2025)

AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization
di: He, Dailan, et al.
Pubblicazione: (2026)

VORTEX: Aligning Task Utility and Human Preferences through LLM-Guided Reward Shaping
di: Xiong, Guojun, et al.
Pubblicazione: (2025)

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception
di: Pang, Ziqi, et al.
Pubblicazione: (2025)

Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics
di: Shen, Ying, et al.
Pubblicazione: (2026)

CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance
di: Deng, Yufan, et al.
Pubblicazione: (2025)

RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation
di: Chen, Yucheng, et al.
Pubblicazione: (2026)

QAEncoder: Towards Aligned Representation Learning in Question Answering Systems
di: Wang, Zhengren, et al.
Pubblicazione: (2024)

PhysVid: Physics Aware Local Conditioning for Generative Video Models
di: Pathak, Saurabh, et al.
Pubblicazione: (2026)