No article text was recorded for this version.
decoupled spatial-temporal training
Version 1 of 152 papers61 conceptsfrozen 2026-10-04
Papers in this version
- Blog: HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
- Blog: NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors
- Blog: Learning Temporally Consistent Video Depth from Video Diffusion Priors
- Blog: Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation
- Blog: Recursive Multi-Exposure Alignment with Spatiotemporal Decoupling for Efficient Burst HDR and Restoration
- Blog: Dynamic Concepts Personalization from Single Videos
- Blog: Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
- Blog: Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion
- Blog: OmniVL: One Foundation Model for Image-Language and Video-Language Tasks
- Blog: ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping
- Blog: Image to Video Domain Adaptation Using Web Supervision
- Blog: A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition
- Blog: Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models
- Blog: Follow Your Pose: Pose-Guided Text-to-Video Generation Using Pose-Free Videos
- Blog: Semantic and Temporal Integration in Latent Diffusion Space for High-Fidelity Video Super-Resolution
- Blog: ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping
- Blog: Exocentric-to-Egocentric Video Generation
- Blog: SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior
- Blog: TransVDM: Motion-Constrained Video Diffusion Model for Transparent Video Synthesis
- Blog: DRFusion: Drift-Resilient Temporally Consistent Infrared–Visible Video Fusion
- Blog: PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling
- Blog: Image-to-video Adaptation with Outlier Modeling and Robust Self-learning
- Blog: Animate Your Motion: Turning Still Images into Dynamic Videos
- Blog: CronusVLA: Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
- Blog: Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images
- Blog: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
- Blog: Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
- Blog: Edit-Your-Motion: Space-Time Diffusion Decoupling Learning for Video Motion Editing
- Blog: Temporally Consistent Enhancement of Low-Light Videos via Spatial-Temporal Compatible Learning
- Blog: An Unsupervised Temporal Consistency (TC) Loss To Improve the Performance of Semantic Segmentation Networks
- Blog: Mission Balance: Generating Under-represented Class Samples using Video Diffusion Models
- Blog: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
- Blog: DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
- Blog: CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video
- Blog: Motion-Aware Memory Network for Fast Video Salient Object Detection
- Blog: TiVGAN: Text to Image to Video Generation With Step-by-Step Evolutionary Generator
- Blog: H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions.
- Blog: Foundation Model Driven Appearance Extraction for Robust Multiple Object Tracking
- Blog: B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding
- Blog: Self-Supervised Transformers for fMRI representation
- Blog: Learning Effective Dynamics across Spatio-Temporal Scales of Complex Flows
- Blog: DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
- Blog: Every Image Listens, Every Image Dances: Music-Driven Image Animation
- Blog: MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
- Blog: Learning Sequential Contexts using Transformer for 3D Hand Pose Estimation
- Blog: ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling
- Blog: GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR
- Blog: Learning visual motion in recurrent neural networks
- Blog: MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos
- Blog: VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models
- Blog: MoTrans: Customized Motion Transfer with Text-driven Video Diffusion Models
- Blog: BEVT: BERT Pretraining of Video Transformers
History & citation
Current · Permanent link
- This direction split from Decoupling Appearance and Motion in Generative Video Models (92% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_decoupled_spatial_temporal_training_408608f1,
title = {decoupled spatial-temporal training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/decoupled-spatial-temporal-training/rdr_408608f1e5f64ef6a0de5977fb868622},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_decoupled_spatial_temporal_training_408608f1_v1,
title = {decoupled spatial-temporal training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/decoupled-spatial-temporal-training/rdr_408608f1e5f64ef6a0de5977fb868622/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}