MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
hub
Freenoise: Tuning-free longer video diffusion via noise rescheduling.arXiv preprint arXiv:2310.15169
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
abstract
With the availability of large-scale video datasets and the advances of diffusion models, text-driven video generation has achieved substantial progress. However, existing video generation models are typically trained on a limited number of frames, resulting in the inability to generate high-fidelity long videos during inference. Furthermore, these models only support single-text conditions, whereas real-life scenarios often require multi-text conditions as the video content changes over time. To tackle these challenges, this study explores the potential of extending the text-driven capability to generate longer videos conditioned on multiple texts. 1) We first analyze the impact of initial noise in video diffusion models. Then building upon the observation of noise, we propose FreeNoise, a tuning-free and time-efficient paradigm to enhance the generative capabilities of pretrained video diffusion models while preserving content consistency. Specifically, instead of initializing noises for all frames, we reschedule a sequence of noises for long-range correlation and perform temporal attention over them by window-based function. 2) Additionally, we design a novel motion injection method to support the generation of videos conditioned on multiple text prompts. Extensive experiments validate the superiority of our paradigm in extending the generative capabilities of video diffusion models. It is noteworthy that compared with the previous best-performing method which brought about 255% extra time cost, our method incurs only negligible time cost of approximately 17%. Generated video samples are available at our website: http://haonanqiu.com/projects/FreeNoise.html.
hub tools
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 17roles
background 2polarities
background 2representative citing papers
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
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.
PermaVid disentangles spatial context into semantic appearance and geometric structure via multi-modal memory banks and edit-aware updates to maintain long-term consistency in video generation after edits.
GIM-World adds a camera-queryable geometry distillation head and pruning rule to implicit memory in video world models, claiming better long-horizon geometric consistency on the MIND benchmark than explicit and implicit baselines.
MIGA introduces two-stage alignment to close train-inference gaps and dual consistency enhancement via self-reflection and long-range guidance to achieve SOTA temporal consistency in infinite-frame video generation on VBench and NarrLV.
HorizonDrive is a new anti-drifting autoregressive training and distillation method that enables minute-scale stable driving video rollouts by making the teacher model rollout-capable via scheduled rollout recovery and teacher rollout DMD.
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
RAPO++ is a three-stage prompt optimization framework combining retrieval-augmented refinement, closed-loop test-time scaling, and LLM fine-tuning to enhance text-to-video generation quality.
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.
DecMem proposes a decoupled memory system using sparse global and anchored local components to enable consistent minute-long controllable video generation in world models.
Matrix-Game 2.0 introduces a scalable data pipeline, action-injection module, and few-step distillation to enable real-time streaming video generation at 25 FPS from game-engine interactions, with open-sourced weights and code.
A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.
A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.
A prompt fusion approach combines bidirectional time-weighted latent blending, dynamics-informed prompt weighting via CLIP, and semantic action representations to produce temporally consistent long videos from text without retraining.
citing papers explorer
-
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
MBench is a new benchmark that quantifies long-term memory in video world models via three hierarchical consistency dimensions evaluated on curated real videos.
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
-
DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
-
Efficient Video Diffusion Models: Advancements and Challenges
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
-
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.
-
PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
PermaVid disentangles spatial context into semantic appearance and geometric structure via multi-modal memory banks and edit-aware updates to maintain long-term consistency in video generation after edits.
-
Geometry-Aware Implicit Memory for Video World Models
GIM-World adds a camera-queryable geometry distillation head and pruning rule to implicit memory in video world models, claiming better long-horizon geometric consistency on the MIND benchmark than explicit and implicit baselines.
-
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
MIGA introduces two-stage alignment to close train-inference gaps and dual consistency enhancement via self-reflection and long-range guidance to achieve SOTA temporal consistency in infinite-frame video generation on VBench and NarrLV.
-
HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation
HorizonDrive is a new anti-drifting autoregressive training and distillation method that enables minute-scale stable driving video rollouts by making the teacher model rollout-capable via scheduled rollout recovery and teacher rollout DMD.
-
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
-
RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
RAPO++ is a three-stage prompt optimization framework combining retrieval-augmented refinement, closed-loop test-time scaling, and LLM fine-tuning to enhance text-to-video generation quality.
-
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.
-
DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
DecMem proposes a decoupled memory system using sparse global and anchored local components to enable consistent minute-long controllable video generation in world models.
-
Matrix-game 2.0: An open-source real-time and streaming interactive world model
Matrix-Game 2.0 introduces a scalable data pipeline, action-injection module, and few-step distillation to enable real-time streaming video generation at 25 FPS from game-engine interactions, with open-sourced weights and code.
-
Movie Gen: A Cast of Media Foundation Models
A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.
-
Character-Centered Dialogue Generation from Scene-Level Prompts
A training-free framework generates expressive, character-grounded dialogue and speech from scene prompts using vision-language encoders, LLMs, and a recursive narrative memory bank for cross-scene consistency.
-
Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling
A prompt fusion approach combines bidirectional time-weighted latent blending, dynamics-informed prompt weighting via CLIP, and semantic action representations to produce temporally consistent long videos from text without retraining.