AI Paper Atlas

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

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
use DropletVideo instead of Nvidia-CosmosI2V generation · VBench++ I2V (ISTP prompts)Camera Motion: 37.56 -> 37.93Improved
use DropletVideo instead of I2VGen-XLI2V generation · VBench++ I2V (ISTP prompts)Camera Motion: 12.95 -> 37.93Improved
use DropletVideo instead of Animate-AnythingI2V generation · VBench++ I2V (ISTP prompts)Camera Motion: 10.64 -> 37.93Improved
use DropletVideo instead of Animate-AnythingI2V generation · VBench++ I2V (ISTP prompts)I2V Subject: 98.13 -> 98.51Improved
use DropletVideo instead of Animate-AnythingI2V generation · VBench++ I2V (ISTP prompts)I2V Background: 96.05 -> 96.74Improved
use DropletVideo instead of Nvidia-CosmosI2V generation · VBench++ I2V (ISTP prompts)Motion Smoothness: 98.82 -> 98.94Improved
use DropletVideo instead of Nvidia-CosmosI2V generation · VBench++ I2V (ISTP prompts)Dynamic Degree: 83.90 -> 27.97Hurt
use DropletVideo instead of Animate-AnythingI2V generation · VBench++ I2V (ISTP prompts)Aesthetic Quality: 66.42 -> 60.94Hurt
use DropletVideo instead of Animate-AnythingI2V generation · VBench++ I2V (ISTP prompts)Subject Consistency: 98.18 -> 96.54Hurt
lower motion control parameter M from 16 to 8DropletVideo · Qualitative motion controlcamera movement: M=8 vs M=12, M=16Improved
fine-tune InternVL2-8B captioner on about 600 curated samplesvideo captioning · Caption quality (human ratings)caption detailImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy