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.
Boximator: Generating rich and controllable motions for video synthesis
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
Generating rich and controllable motion is a pivotal challenge in video synthesis. We propose Boximator, a new approach for fine-grained motion control. Boximator introduces two constraint types: hard box and soft box. Users select objects in the conditional frame using hard boxes and then use either type of boxes to roughly or rigorously define the object's position, shape, or motion path in future frames. Boximator functions as a plug-in for existing video diffusion models. Its training process preserves the base model's knowledge by freezing the original weights and training only the control module. To address training challenges, we introduce a novel self-tracking technique that greatly simplifies the learning of box-object correlations. Empirically, Boximator achieves state-of-the-art video quality (FVD) scores, improving on two base models, and further enhanced after incorporating box constraints. Its robust motion controllability is validated by drastic increases in the bounding box alignment metric. Human evaluation also shows that users favor Boximator generation results over the base model.
citation-role summary
background 3
citation-polarity summary
fields
cs.CV 12years
2026 12roles
background 3polarities
background 3representative citing papers
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.
Fine-tuning CogVideoX with autoregressive context management and bidirectional alignment enables a single model to perform event-based video reconstruction, prediction, and zero-shot interpolation with superior temporal stability.
LooseControlVideo fine-tunes a video model on DNOCS-annotated data to enable layout and trajectory control via oriented 3D boxes, reporting 1.2-3x gains in trajectory accuracy over 2D baselines on nuScenes, HO-3D and BEHAVE.
T2Mo generates controllable dynamic 3D shapes by conditioning on both text semantics and 3D trajectories with a shape-grounded embedding for arbitrary inputs.
CVG improves compositional faithfulness in frozen text-to-video diffusion models by steering early denoising steps with gradients from a classifier trained on the model's own cross-attention features.
PhyCo adds continuous physical control to video diffusion models via physics-supervised fine-tuning on a large simulation dataset and VLM-guided rewards, yielding measurable gains in physical realism on the Physics-IQ benchmark.
LiVER conditions video diffusion models on renderer-derived 3D control signals for disentangled, editable control over object layout, lighting, and camera trajectory.
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.
A video world model framework that uses LLM-orchestrated 3D trajectories as control signals for generation to achieve persistent dynamic object memory and viewpoint freedom.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
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.
-
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
Fine-tuning CogVideoX with autoregressive context management and bidirectional alignment enables a single model to perform event-based video reconstruction, prediction, and zero-shot interpolation with superior temporal stability.
-
LooseControlVideo: Directorial Video Control using Spatial Blocking
LooseControlVideo fine-tunes a video model on DNOCS-annotated data to enable layout and trajectory control via oriented 3D boxes, reporting 1.2-3x gains in trajectory accuracy over 2D baselines on nuScenes, HO-3D and BEHAVE.
-
Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text
T2Mo generates controllable dynamic 3D shapes by conditioning on both text semantics and 3D trajectories with a shape-grounded embedding for arbitrary inputs.
-
Compositional Video Generation via Inference-Time Guidance
CVG improves compositional faithfulness in frozen text-to-video diffusion models by steering early denoising steps with gradients from a classifier trained on the model's own cross-attention features.
-
PhyCo: Learning Controllable Physical Priors for Generative Motion
PhyCo adds continuous physical control to video diffusion models via physics-supervised fine-tuning on a large simulation dataset and VLM-guided rewards, yielding measurable gains in physical realism on the Physics-IQ benchmark.
-
Lighting-grounded Video Generation with Renderer-based Agent Reasoning
LiVER conditions video diffusion models on renderer-derived 3D control signals for disentangled, editable control over object layout, lighting, and camera trajectory.
-
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.
-
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory
A video world model framework that uses LLM-orchestrated 3D trajectories as control signals for generation to achieve persistent dynamic object memory and viewpoint freedom.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.