TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
hub Mixed citations
arXiv preprint arXiv:2502.02492 , year=
Mixed citation behavior. Most common role is background (67%).
18
Pith papers citing it
Background
67% of classified citations
hub tools
citation-role summary
background 4
method 1
other 1
citation-polarity summary
fields
cs.CV 18representative 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.
A framework for consistent long-horizon video relighting that propagates target latents across chunks and trains continuation via masked target-domain self-conditioning plus warm-start prompting.
NEXUS introduces a graph-based neural energy-field model that derives forces from scalar energy and dissipation terms to achieve physically consistent contact-rich 3D dynamics.
SpecLoR rectifies the amplitude spectrum of lookahead-estimated clean latents to natural-video priors during early ODE sampling steps, cutting physical artifacts with only four extra NFEs.
LaMo adds self-supervised latent motion priors via a motion drift loss during training and motion prior guidance during sampling to boost physical fidelity in video diffusion models like CogVideoX.
PhyMotion scores generated human videos by grounding recovered 3D poses in a physics simulator across kinematic, contact, and dynamic axes, yielding stronger human correlation and larger RL post-training gains than prior 2D rewards.
Video-LLMs fail physical reasoning due to semantic prior dominance rather than perception deficits; a new programmatic adversarial curriculum and visual-anchored reasoning chain enable substantial gains via standard LoRA fine-tuning.
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
OptiWorld inserts a classical optimal-control layer that extracts a world state, plans an optimal trajectory on a geometric manifold under physical constraints, and renders the video conditioned on that trajectory.
Tempered Self-similarity Alignment transfers relational structure from foundation-model STSS into video generators via probabilistic correspondence alignment, yielding reported gains in physical plausibility on VideoPhy benchmarks.
Introduces dual pose-image representation, cross-modal alignment, and iterative construction to improve prompt alignment and diversity in multi-person text-to-image generation.
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
Motus unifies understanding, video generation, and action in one latent world model via MoT experts and optical-flow latent actions, reporting gains over prior methods in simulation and real robots.
MusicInfuser uses a novel layer-wise adaptability criterion to adapt text-to-video diffusion models for generating music-synchronized dance videos with limited training on a single GPU.
ST-DRC proposes latent in-context injection, TASS-RoPE, appearance-invariant augmentation, and three-stream guidance to improve identity preservation in text-to-video diffusion models built on LTX-2.3.
citing papers explorer
-
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
-
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.
-
HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers
A framework for consistent long-horizon video relighting that propagates target latents across chunks and trains continuation via masked target-domain self-conditioning plus warm-start prompting.
-
NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics
NEXUS introduces a graph-based neural energy-field model that derives forces from scalar energy and dissipation terms to achieve physically consistent contact-rich 3D dynamics.
-
SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation
SpecLoR rectifies the amplitude spectrum of lookahead-estimated clean latents to natural-video priors during early ODE sampling steps, cutting physical artifacts with only four extra NFEs.
-
LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation
LaMo adds self-supervised latent motion priors via a motion drift loss during training and motion prior guidance during sampling to boost physical fidelity in video diffusion models like CogVideoX.
-
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
PhyMotion scores generated human videos by grounding recovered 3D poses in a physics simulator across kinematic, contact, and dynamic axes, yielding stronger human correlation and larger RL post-training gains than prior 2D rewards.
-
From Priors to Perception: Grounding Video-LLMs in Physical Reality
Video-LLMs fail physical reasoning due to semantic prior dominance rather than perception deficits; a new programmatic adversarial curriculum and visual-anchored reasoning chain enable substantial gains via standard LoRA fine-tuning.
-
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
OptiWorld: Optimal Control for Video World Generation under Physical Constraints
OptiWorld inserts a classical optimal-control layer that extracts a world state, plans an optimal trajectory on a geometric manifold under physical constraints, and renders the video conditioned on that trajectory.
-
Tempered Self-Similarity Alignment for Physically Plausible Video Generation
Tempered Self-similarity Alignment transfers relational structure from foundation-model STSS into video generators via probabilistic correspondence alignment, yielding reported gains in physical plausibility on VideoPhy benchmarks.
-
Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes
Introduces dual pose-image representation, cross-modal alignment, and iterative construction to improve prompt alignment and diversity in multi-person text-to-image generation.
-
Reward-Forcing: Autoregressive Video Generation with Reward Feedback
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
-
Motus: A Unified Latent Action World Model
Motus unifies understanding, video generation, and action in one latent world model via MoT experts and optical-flow latent actions, reporting gains over prior methods in simulation and real robots.
-
MusicInfuser: Making Video Diffusion Listen and Dance
MusicInfuser uses a novel layer-wise adaptability criterion to adapt text-to-video diffusion models for generating music-synchronized dance videos with limited training on a single GPU.
-
Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation
ST-DRC proposes latent in-context injection, TASS-RoPE, appearance-invariant augmentation, and three-stream guidance to improve identity preservation in text-to-video diffusion models built on LTX-2.3.