REVIEW 14 cited by
VBench: Comprehensive Benchmark Suite for Video Generative Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide insights to inform future developments of video generation. To this end, we present VBench, a comprehensive benchmark suite that dissects "video generation quality" into specific, hierarchical, and disentangled dimensions, each with tailored prompts and evaluation methods. VBench has three appealing properties: 1) Comprehensive Dimensions: VBench comprises 16 dimensions in video generation (e.g., subject identity inconsistency, motion smoothness, temporal flickering, and spatial relationship, etc). The evaluation metrics with fine-grained levels reveal individual models' strengths and weaknesses. 2) Human Alignment: We also provide a dataset of human preference annotations to validate our benchmarks' alignment with human perception, for each evaluation dimension respectively. 3) Valuable Insights: We look into current models' ability across various evaluation dimensions, and various content types. We also investigate the gaps between video and image generation models. We will open-source VBench, including all prompts, evaluation methods, generated videos, and human preference annotations, and also include more video generation models in VBench to drive forward the field of video generation.
Forward citations
Cited by 14 Pith papers
-
Parallel Decoding Distillation for Fast Image and Video Generation
A trajectory-based distillation method trains a student to predict multiple mean velocities per network evaluation, enabling 4-8 step generation with competitive quality and improved diversity.
-
CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion
Using cached drafts to select the winner and regenerating only that winner captures 94.7% of best-of-8 search gain at 63% of the cost.
-
Adaptive Identity Anchoring: Closed-Loop Keyframe Placement for Synthetic Paired Supervision in Video Face Swapping
For video face swapping, adaptively adding swapped anchor frames at the moments of worst identity drift should make synthetic training pairs more faithful than the current first-and-last-frame-only scheme.
-
PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation
Iteratively simulating, verifying, and repairing physics programs gives video generation more reliable fine-grained control over object motion than one-shot configuration.
-
CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation
Disaggregating cache operators from compute and overlapping them across the two classifier-free-guidance branches turns cross-timestep caching into up to 1.80x real end-to-end speedup on edge GPUs when the cache overf...
-
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
Hallo4D uses vision-language models to detect and correct spatial and temporal mistakes in AI-generated 3D and 4D content, improving consistency without retraining the base generators.
-
Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
A training-free predictor-corrector method that accelerates Diffusion Transformers by solving a feature-ODE, achieving large compute reductions with modest quality loss.
-
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
CineScale extends pre-trained diffusion models to 8k image and 4k video generation with mostly tuning-free inference plus a small LoRA adaptation for video.
-
FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion
FreeLong++ extends short-video diffusion models to 4x to 8x longer clips, without retraining, by fusing multiple windowed attention branches through frequency-domain filters and a spectral noise initialization.
-
VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment
A VGGT-based pointwise reprojection reward with geometry-aware sampling improves video geometric consistency via SFT/DPO and causal test-time search.
-
Extended Field of View Analysis for VideoGAN-based Trajectory Generation
A video GAN trained on semantic top-down traffic videos generates 15–25 m field-of-view scenes whose speed, acceleration, spacing, and time-to-collision statistics resemble real Waymo data, with inference below 20 ms.
-
From Sound to Sight: Towards AI-authored Music Videos
This paper presents two off-the-shelf model pipelines (CLAP or LALM, an LLM, and a text-to-video model) for generating music videos from arbitrary songs, validated by a preliminary five-participant user study with mod...
-
AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation
A finetuned vision-language model jointly predicts nine aspect scores and written comments for AI-generated videos, with a new benchmark and claims of state-of-the-art alignment with human judgment.
-
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
PAROAttention permutes tokens along frame, height, and width axes to make visual attention block-wise, enabling sparse and INT8/INT4 quantized attention with near-baseline generation quality.
Discussion (0). Sign in to comment.