Research map / Video / Video generation
DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
Runze Zhang, Guoguang Du, Xiaochuan Li, Qi Jia, Liang Jin, Lu Liu, Jingjing Wang, Cong Xu, Zhenhua Guo, Yaqian Zhao, Xiaoli Gong, Rengang Li and 1 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use DropletVideo instead of Nvidia-Cosmos | I2V generation · VBench++ I2V (ISTP prompts) | Camera Motion: 37.56 -> 37.93 | Improved |
| use DropletVideo instead of I2VGen-XL | I2V generation · VBench++ I2V (ISTP prompts) | Camera Motion: 12.95 -> 37.93 | Improved |
| use DropletVideo instead of Animate-Anything | I2V generation · VBench++ I2V (ISTP prompts) | Camera Motion: 10.64 -> 37.93 | Improved |
| use DropletVideo instead of Animate-Anything | I2V generation · VBench++ I2V (ISTP prompts) | I2V Subject: 98.13 -> 98.51 | Improved |
| use DropletVideo instead of Animate-Anything | I2V generation · VBench++ I2V (ISTP prompts) | I2V Background: 96.05 -> 96.74 | Improved |
| use DropletVideo instead of Nvidia-Cosmos | I2V generation · VBench++ I2V (ISTP prompts) | Motion Smoothness: 98.82 -> 98.94 | Improved |
| use DropletVideo instead of Nvidia-Cosmos | I2V generation · VBench++ I2V (ISTP prompts) | Dynamic Degree: 83.90 -> 27.97 | Hurt |
| use DropletVideo instead of Animate-Anything | I2V generation · VBench++ I2V (ISTP prompts) | Aesthetic Quality: 66.42 -> 60.94 | Hurt |
| use DropletVideo instead of Animate-Anything | I2V generation · VBench++ I2V (ISTP prompts) | Subject Consistency: 98.18 -> 96.54 | Hurt |
| lower motion control parameter M from 16 to 8 | DropletVideo · Qualitative motion control | camera movement: M=8 vs M=12, M=16 | Improved |
| fine-tune InternVL2-8B captioner on about 600 curated samples | video captioning · Caption quality (human ratings) | caption detail | Improved |
Closest papers by meaning
- Direct Motion Models for Assessing Generated Videos (ICML 2025 · similarity 0.88)
- Video World Models with Long-term Spatial Memory (NeurIPS 2025 · similarity 0.88)
- StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation (CVPR 2025 · similarity 0.87)
- FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation (NeurIPS 2025 · similarity 0.87)
- Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation (CVPR 2024 · similarity 0.87)
- Generative Inbetweening through Frame-wise Conditions-Driven Video Generation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
