AI Paper Atlas

Research map / Video / Video generation

GraphVid: Interactive Graph-Controllable Video Generation

Vedant Shah, Onkar Susladkar, Tushar Prakash, Kiet Nguyen, Tianjiao (Joey) Yu, Adheesh Juvekar, Muntasir Wahed, Ismini Lourentzou

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 0 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 directed interaction graph conditioning instead of text+image (ablation)GraphVid (LTX-Video) · MoveBench interaction subsetFID: 20.04 -> 17.02Improved
add semantic edge text to topology-only graph (ablation)GraphVid · MoveBench interaction subsetFID: 17.52 -> 17.02Improved
add semantic edge text to topology-only graph (ablation)GraphVid · MoveBench interaction subsetPSNR: 16.88 -> 15.98Hurt
add edge embeddings and message passing (ablation)GraphVid · MoveBench interaction subsetFID: 19.55 -> 17.02Improved
increase LoRA rank from 16 to 128 (ablation)GraphVid · MoveBench interaction subsetFID: 18.34 -> 17.02Improved
increase max node capacity from 30 to 256 (ablation)GraphVid · MoveBench interaction subsetFVD: 99.42 -> 109.92Hurt
reduce max node capacity from 30 to 10 (ablation)GraphVid · MoveBench interaction subsetFVD: 99.42 -> 102.04Hurt
swap LTX backbone for Wan 2.2 (ablation)GraphVid · MoveBench interaction subsetFID: 17.02 -> 17.29No clear effect
graph conditioning vs WISA physics textGraphVid · MoveBench interaction subsetFID: 25.98 -> 17.02Improved
graph conditioning vs Motion-I2VGraphVid · MoveBench interaction subsetPSNR: 9.87 -> 15.98Improved
GraphVid vs Wan-Move (large-scale)GraphVid · MoveBench interaction subsetFID: 15.56 vs 17.02Hurt
graph conditioning on multi-object scenes vs FlashMotionGraphVid · MoveBench multi-object subsetFID: 55.03 -> 49.45Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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