TrajLoc enforces per-object trajectory constraints in I2V generation via attention-layer Gaussian heatmap substitution, yielding +4.3 dB PSNR and 51% lower endpoint error on datasets with up to 20 objects across two backbones.
arXiv preprint arXiv:2505.22944 (2025)
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
years
2026 12verdicts
UNVERDICTED 12representative citing papers
FLAT maps compressed video diffusion latents to explicit triangle splats via ray-centered rotation parameterization and a product window function, reporting better geometric accuracy than 3D Gaussian baselines under identical training.
SVI-Bench provides 35K hours of sports video with 9 tasks across four cognitive levels, revealing models drop from ~74% on action QA to 5% on agentic evidence integration.
PREX decomposes target 4D video volumes into Preserve, Reveal, and Expand roles with a region-aware adapter on a frozen diffusion backbone, trained via proxy tasks, and introduces the PREBench benchmark to reduce region-structured editing failures.
MoRight disentangles object and camera motion via canonical-view specification and temporal cross-view attention, while decomposing motion into active user-driven and passive consequence components to learn and apply causality in video generation.
A synthetic data pipeline and fine-tuned video model enable generative editing to move object 3D trajectories in videos while keeping relative motion.
EO-WM is a diffusion transformer that adds physically separated baseline-anomaly and cumulative-stress conditioning to probabilistic EO forecasting and validates it on two new weather-response benchmarks, reporting 5.63% and 7.80% relative gains on NDVI decline metrics.
GIVE uses paired depth-box and orientation-box geometry streams plus a graphics pipeline to train models for consistent object-level geometric edits like translate, rotate, and scale in videos.
Self-supervised models learn to perceive and manipulate the flow of time in videos, supporting speed detection, large-scale slow-motion data curation, and temporally controllable video synthesis.
Sparse 3D hand joints plus an occlusion-aware control module produce higher-fidelity, 3D-consistent egocentric hand-object videos than dense-2D or implicit-pose baselines.
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.
Adjacent-frame Eulerian optical-flow guidance plus bidirectional geometric consistency is claimed to accelerate training and reduce drift in diffusion-based image animation versus Lagrangian baselines.
citing papers explorer
-
TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control
TrajLoc enforces per-object trajectory constraints in I2V generation via attention-layer Gaussian heatmap substitution, yielding +4.3 dB PSNR and 51% lower endpoint error on datasets with up to 20 objects across two backbones.
-
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
FLAT maps compressed video diffusion latents to explicit triangle splats via ray-centered rotation parameterization and a product window function, reporting better geometric accuracy than 3D Gaussian baselines under identical training.
-
SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence
SVI-Bench provides 35K hours of sports video with 9 tasks across four cognitive levels, revealing models drop from ~74% on action QA to 5% on agentic evidence integration.
-
Preserve, Reveal, Expand: Faithful 4D Video Editing with Region-Aware Conditioning
PREX decomposes target 4D video volumes into Preserve, Reveal, and Expand roles with a region-aware adapter on a frozen diffusion backbone, trained via proxy tasks, and introduces the PREBench benchmark to reduce region-structured editing failures.
-
MoRight: Motion Control Done Right
MoRight disentangles object and camera motion via canonical-view specification and temporal cross-view attention, while decomposing motion into active user-driven and passive consequence components to learn and apply causality in video generation.
-
TrajectoryMover: Generative Movement of Object Trajectories in Videos
A synthetic data pipeline and fine-tuned video model enable generative editing to move object 3D trajectories in videos while keeping relative motion.
-
EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting
EO-WM is a diffusion transformer that adds physically separated baseline-anomaly and cumulative-stress conditioning to probabilistic EO forecasting and validates it on two new weather-response benchmarks, reporting 5.63% and 7.80% relative gains on NDVI decline metrics.
-
Geometry-Instructed Video Editing
GIVE uses paired depth-box and orientation-box geometry streams plus a graphics pipeline to train models for consistent object-level geometric edits like translate, rotate, and scale in videos.
-
Seeing Fast and Slow: Learning the Flow of Time in Videos
Self-supervised models learn to perceive and manipulate the flow of time in videos, supporting speed detection, large-scale slow-motion data curation, and temporally controllable video synthesis.
-
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
Sparse 3D hand joints plus an occlusion-aware control module produce higher-fidelity, 3D-consistent egocentric hand-object videos than dense-2D or implicit-pose baselines.
-
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.
-
Eulerian Motion Guidance: Robust Image Animation via Bidirectional Geometric Consistency
Adjacent-frame Eulerian optical-flow guidance plus bidirectional geometric consistency is claimed to accelerate training and reduce drift in diffusion-based image animation versus Lagrangian baselines.