Image de couverture de livre

Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Liying, Liu, Chen, Zhu, Zhenwei, Liu, Ajian, Ma, Hui, Nong, Jian, Liang, Yanyan
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

PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning
par: Yu, Xinxing, et autres
Publié: (2026)

FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection
par: Li, Yongze, et autres
Publié: (2025)

Not All Pixels Are Equal: Confidence-Guided Attention for Feature Matching
par: Li, Dongyue
Publié: (2025)

Not All Points Are Equal: Uncertainty-Aware 4D LiDAR Scene Synthesis
par: Xu, Xiang, et autres
Publié: (2026)

Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors
par: Zhou, Pengfei, et autres
Publié: (2026)

M^3Detection: Multi-Frame Multi-Level Feature Fusion for Multi-Modal 3D Object Detection with Camera and 4D Imaging Radar
par: Li, Xiaozhi, et autres
Publié: (2025)

Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generation
par: Yang, Liying, et autres
Publié: (2026)

Dynamic Feature Learning and Matching for Class-Incremental Learning
par: Qiang, Sunyuan, et autres
Publié: (2024)

Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrieval
par: Liu, Yang, et autres
Publié: (2024)

Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction
par: Cai, Xudong, et autres
Publié: (2025)

Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting
par: Lin, Jiaqi, et autres
Publié: (2025)

Distilling Future Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection
par: Zheng, Haowen, et autres
Publié: (2025)

FreeDriveRF: Monocular RGB Dynamic NeRF without Poses for Autonomous Driving via Point-Level Dynamic-Static Decoupling
par: Wen, Yue, et autres
Publié: (2025)

LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling
par: Wu, Jiahao, et autres
Publié: (2025)

CAD-SLAM: Consistency-Aware Dynamic SLAM with Dynamic-Static Decoupled Mapping
par: Wu, Wenhua, et autres
Publié: (2025)

Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution
par: Wang, Hongjun, et autres
Publié: (2025)

Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning
par: Yang, Songyuan, et autres
Publié: (2026)

Learning Causal Features for Incremental Object Detection
par: He, Zhenwei, et autres
Publié: (2024)

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
par: Zhou, Shijie, et autres
Publié: (2025)

Distilling Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection
par: Zheng, Haowen, et autres
Publié: (2024)

Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering
par: Guo, Jiabao, et autres
Publié: (2025)

Decouple to Reconstruct: High Quality UHD Restoration via Active Feature Disentanglement and Reversible Fusion
par: Liu, Yidi, et autres
Publié: (2025)

Object-Aware Video Matting with Cross-Frame Guidance
par: Zhang, Huayu, et autres
Publié: (2025)

Not All Modalities Are Equal: Instruction-Aware Gating for Multimodal Videos
par: Ding, Bonan, et autres
Publié: (2026)

FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks
par: Li, Jinwei, et autres
Publié: (2025)

HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
par: Wang, Boyuan, et autres
Publié: (2025)

MEDN: Motion-Emotion Feature Decoupling Network for Micro-Expression Recognition
par: Hu, Chenxing, et autres
Publié: (2026)

SDD-4DGS: Static-Dynamic Aware Decoupling in Gaussian Splatting for 4D Scene Reconstruction
par: Sun, Dai, et autres
Publié: (2025)

FeTT: Continual Class Incremental Learning via Feature Transformation Tuning
par: Qiang, Sunyuan, et autres
Publié: (2024)

GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth
par: Liu, Yuecheng, et autres
Publié: (2026)

Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation
par: Wang, Song, et autres
Publié: (2024)

Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model
par: Wang, Yuan, et autres
Publié: (2026)

TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction
par: Ma, Yukuo, et autres
Publié: (2025)

Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
par: Liu, Yang, et autres
Publié: (2023)

YOLO-DS: Fine-Grained Feature Decoupling via Dual-Statistic Synergy Operator for Object Detection
par: Huang, Lin, et autres
Publié: (2026)

Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
par: He, Shuting, et autres
Publié: (2024)

D3: Training-Free AI-Generated Video Detection Using Second-Order Features
par: Zheng, Chende, et autres
Publié: (2025)

See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
par: Lu, Dongyue, et autres
Publié: (2025)

DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification
par: Wang, Yuhao, et autres
Publié: (2024)

FeatureFool: Zero-Query Fooling of Video Models via Feature Map
par: Tang, Duoxun, et autres
Publié: (2025)