Image de couverture de livre

FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Kuanting, Ota, Kei, Kanezaki, Asako
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Zero-Shot Peg Insertion: Identifying Mating Holes and Estimating SE(2) Poses with Vision-Language Models
par: Yajima, Masaru, et autres
Publié: (2025)

Embodied Navigation with Auxiliary Task of Action Description Prediction
par: Kondoh, Haru, et autres
Publié: (2025)

OP-Align: Object-level and Part-level Alignment for Self-supervised Category-level Articulated Object Pose Estimation
par: Che, Yuchen, et autres
Publié: (2024)

COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation
par: Che, Yuchen, et autres
Publié: (2026)

Zero-shot Degree of Ill-posedness Estimation for Active Small Object Change Detection
par: Takeda, Koji, et autres
Publié: (2024)

Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation
par: Sun, Leyuan, et autres
Publié: (2024)

3D Segmentation Using Viewpoint-Dependent Spatial Relationships
par: Nanri, Ayaka, et autres
Publié: (2026)

VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
par: Zhu, Ziyue, et autres
Publié: (2025)

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation
par: Cheng, Ho Kei, et autres
Publié: (2025)

Flow-Guided Diffusion for Video Inpainting
par: Gu, Bohai, et autres
Publié: (2023)

RFDM: Residual Flow Diffusion Model for Efficient Causal Video Editing
par: Salehi, Mohammadreza, et autres
Publié: (2026)

Latent Temporal Discrepancy as Motion Prior: A Loss-Weighting Strategy for Dynamic Fidelity in T2V
par: Wu, Meiqi, et autres
Publié: (2026)

FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation
par: Zhang, Zekang, et autres
Publié: (2026)

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
par: Gu, Yuchao, et autres
Publié: (2026)

An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting
par: Lin, Dongdong, et autres
Publié: (2024)

Efficient Diffusion Distillation via Embedding Loss
par: Ying, Jincheng, et autres
Publié: (2026)

FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis
par: Jin, Wonjoon, et autres
Publié: (2025)

TransFlow: Motion Knowledge Transfer from Video Diffusion Models to Video Salient Object Detection
par: Cho, Suhwan, et autres
Publié: (2025)

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models
par: Min, Jaewon, et autres
Publié: (2026)

FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models
par: Li, Minghan, et autres
Publié: (2025)

Efficient Continuous Video Flow Model for Video Prediction
par: Shrivastava, Gaurav, et autres
Publié: (2024)

Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models
par: Li, Qifan, et autres
Publié: (2026)

FashionFlow: Leveraging Diffusion Models for Dynamic Fashion Video Synthesis from Static Imagery
par: Islam, Tasin, et autres
Publié: (2023)

Diffusion Model with Perceptual Loss
par: Lin, Shanchuan, et autres
Publié: (2023)

PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation
par: Liu, Zhuoman, et autres
Publié: (2024)

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
par: Zhu, Yuanzhi, et autres
Publié: (2024)

Enhancing Video Memorability Prediction with Text-Motion Cross-modal Contrastive Loss and Its Application in Video Summarization
par: Zhu, Zhiyi, et autres
Publié: (2025)

Coherent Video Inpainting Using Optical Flow-Guided Efficient Diffusion
par: Gu, Bohai, et autres
Publié: (2024)

Goku: Flow Based Video Generative Foundation Models
par: Chen, Shoufa, et autres
Publié: (2025)

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
par: Burgert, Ryan, et autres
Publié: (2025)

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
par: Liang, Feng, et autres
Publié: (2023)

Physics-Guided Motion Loss for Video Generation Model
par: Xue, Bowen, et autres
Publié: (2025)

Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
par: Alwis, Praditha, et autres
Publié: (2026)

On Exact Editing of Flow-Based Diffusion Models
par: Li, Zixiang, et autres
Publié: (2025)

Diffusion Models with Deterministic Normalizing Flow Priors
par: Zand, Mohsen, et autres
Publié: (2023)

MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models
par: Meral, Tuna Han Salih, et autres
Publié: (2024)

CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL
par: Ni, Zhenyang, et autres
Publié: (2026)

Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution
par: Yuan, Yutao, et autres
Publié: (2024)

Layout Control and Semantic Guidance with Attention Loss Backward for T2I Diffusion Model
par: Li, Guandong
Publié: (2024)

Lie Flow: Video Dynamic Fields Modeling and Predicting with Lie Algebra as Geometric Physics Principle
par: Qiao, Weidong, et autres
Publié: (2026)