ReImagine decouples human appearance from temporal consistency via pretrained image backbones, SMPL-X motion guidance, and training-free video diffusion refinement to generate high-quality controllable videos.
hub
Mim- icmotion: High-quality human motion video generation with confidence-aware pose guidance
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
HumANDiff improves motion consistency in human video generation by sampling diffusion noise on an articulated human body template and adding joint appearance-motion prediction plus a geometric consistency loss.
CoMoVi co-generates 3D human motions and 2D videos synchronously in a single diffusion denoising loop using 3D-to-2D projection and dual-branch diffusion with 3D-2D cross attentions.
One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and token replacement for long videos.
EMOSH proposes an Expressive Human Model with disentangled parameters, coarse-to-fine motion injection, and spatially-aligned conditioning to generate high-fidelity expressive human videos without driving-subject shape leakage.
An end-to-end diffusion model generates backgrounds, relights green-screen actors, and replaces or creates props in one pass, improving over cascaded inpainting plus relighting baselines in user preference and auto metrics.
SCAIL-2 achieves end-to-end character animation via direct video concatenation, in-context mask conditioning, mode-specific RoPE, the synthetic MotionPair-60K dataset, and Bias-Aware DPO, outperforming prior methods on multiple tasks.
DirectAnimator bypasses pose extraction using a Driving Cue Triplet and Same2X training strategy to achieve state-of-the-art human animation quality and robustness from raw videos.
A training-free framework for human image animation that uses preview-guided denoising plus Inversion-Boosted and Reference-Anchored Self-Attention modules to achieve temporal consistency and identity preservation in diffusion models.
Introduces mesh tokenization to condition DiT-based video diffusion models directly on 3D human meshes for motion control without 2D rendering.
EverAnimate restores drifted latent flow trajectories in chunked video generation via persistent latent propagation and restorative flow matching, achieving measurable gains in PSNR, SSIM, LPIPS, and FID over prior long-animation methods with only LoRA tuning.
A dual-contrastive disentanglement method factorizes videos into independent task and embodiment latents, then uses a parameter-efficient adapter on a frozen video diffusion model to synthesize robot executions from single human demonstrations without paired data.
SignVerse-2M provides a 2-million-clip multilingual pose-native dataset for sign language derived from public videos via DWPose preprocessing to enable robust modeling in real-world conditions.
Synthetic data complements real data in diffusion-based controllable human video generation, with effective sample selection improving motion realism, temporal consistency, and identity preservation.
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
SteadyDancer is an I2V framework using condition reconciliation, synergistic pose modulation, and staged training to achieve robust first-frame preservation and coherent motion control in human image animation.
Presents a scene-adaptive 3D human image animation framework using ground-adaptive motion retargeting and viewpoint-adaptive latent fusion to control human and camera trajectories, claiming improvements on two benchmarks.
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
FusionProxy is a distilled diffusion-based fusion module that adds thermal awareness to RGB vision systems in real time as an independent plug-and-play component.
LUNA is an LBS-free neural animation model that maps 2D controls to 3D Gaussian deformations via a transformer motion regressor and hybrid supervision for realistic motion and zero-shot generalization.
citing papers explorer
-
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
ReImagine decouples human appearance from temporal consistency via pretrained image backbones, SMPL-X motion guidance, and training-free video diffusion refinement to generate high-quality controllable videos.
-
HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation
HumANDiff improves motion consistency in human video generation by sampling diffusion noise on an articulated human body template and adding joint appearance-motion prediction plus a geometric consistency loss.
-
CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
CoMoVi co-generates 3D human motions and 2D videos synchronously in a single diffusion denoising loop using 3D-to-2D projection and dual-branch diffusion with 3D-2D cross attentions.
-
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and token replacement for long videos.
-
EMOSH: Expressive Motion and Shape Disentanglement for Human Animation
EMOSH proposes an Expressive Human Model with disentangled parameters, coarse-to-fine motion injection, and spatially-aligned conditioning to generate high-fidelity expressive human videos without driving-subject shape leakage.
-
Cinematic Compositing Using Character-Environment-Harmonized Video Generation Models
An end-to-end diffusion model generates backgrounds, relights green-screen actors, and replaces or creates props in one pass, improving over cascaded inpainting plus relighting baselines in user preference and auto metrics.
-
SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
SCAIL-2 achieves end-to-end character animation via direct video concatenation, in-context mask conditioning, mode-specific RoPE, the synthetic MotionPair-60K dataset, and Bias-Aware DPO, outperforming prior methods on multiple tasks.
-
Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
DirectAnimator bypasses pose extraction using a Driving Cue Triplet and Same2X training strategy to achieve state-of-the-art human animation quality and robustness from raw videos.
-
FreeAnimate: Training-Free Human Image Animation with Preview-Guided Denoising
A training-free framework for human image animation that uses preview-guided denoising plus Inversion-Boosted and Reference-Anchored Self-Attention modules to achieve temporal consistency and identity preservation in diffusion models.
-
Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization
Introduces mesh tokenization to condition DiT-based video diffusion models directly on 3D human meshes for motion control without 2D rendering.
-
EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration
EverAnimate restores drifted latent flow trajectories in chunked video generation via persistent latent propagation and restorative flow matching, achieving measurable gains in PSNR, SSIM, LPIPS, and FID over prior long-animation methods with only LoRA tuning.
-
Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing
A dual-contrastive disentanglement method factorizes videos into independent task and embodiment latents, then uses a parameter-efficient adapter on a frozen video diffusion model to synthesize robot executions from single human demonstrations without paired data.
-
SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages
SignVerse-2M provides a 2-million-clip multilingual pose-native dataset for sign language derived from public videos via DWPose preprocessing to enable robust modeling in real-world conditions.
-
Exploring the Role of Synthetic Data Augmentation in Controllable Human-Centric Video Generation
Synthetic data complements real data in diffusion-based controllable human video generation, with effective sample selection improving motion realism, temporal consistency, and identity preservation.
-
HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis
HVG-3D uses a 3D-aware diffusion architecture with ControlNet to synthesize high-fidelity hand-object interaction videos from 3D control signals, achieving state-of-the-art spatial fidelity and temporal coherence on the TASTE-Rob dataset.
-
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
SteadyDancer is an I2V framework using condition reconciliation, synergistic pose modulation, and staged training to achieve robust first-frame preservation and coherent motion control in human image animation.
-
3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement
Presents a scene-adaptive 3D human image animation framework using ground-adaptive motion retargeting and viewpoint-adaptive latent fusion to control human and camera trajectories, claiming improvements on two benchmarks.
-
Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control
A decoupled-control autoregressive video model using Fast-Slow Memory training, dynamic projection, and staged camera control to produce stable long-horizon outputs with human and viewpoint guidance.
-
Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models
FusionProxy is a distilled diffusion-based fusion module that adds thermal awareness to RGB vision systems in real time as an independent plug-and-play component.
-
LUNA: Learning Universal 3D Human Animation Beyond Skinning
LUNA is an LBS-free neural animation model that maps 2D controls to 3D Gaussian deformations via a transformer motion regressor and hybrid supervision for realistic motion and zero-shot generalization.