ResearchBenchmarksCamera-controlled Text-to-Video Generation on User study (test)Camera-controlled Text-to-Video Generation on User study (test)Follow89.5CAAC3D64.0270.63577.2583.865Nov 27, 2024Evaluation resultsMethodMethodLinksCAMQTAVQOverall ScoreAC3DComparison Baseline=VD...Comparison Baseline=VD3D (FIT), Baseline Backbone=FIT [23]2024.1189.57987.597.595AC3DComparison Baseline=VD...Comparison Baseline=VD3D (DiT), Baseline Backbone=DiT [102]2024.116587.583.59592.5