Results for “scenes”

2 skills

Evaluates geometric consistency in text-to-video generation by measuring structural and motion coherence across camera trajectories, detecting deformation and occlusion artifacts in static scenes.

More results

Tao Train Ocrnet

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for TAO OCRNet models for scene text recognition from cropped text-region images, supporting CTC and attention-based decoders.