SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation
For researchers in non-photorealistic animation, this work addresses the novel-view artifact problem with a data-driven approach, though it is incremental as it builds on existing 3D animation pipelines.
SPECSIA introduces a stylization dataset and a lightweight module (DraViE) to remove novel-view artifacts in drawing-based 3D animation, achieving consistent gains in fidelity and temporal coherence with lower adaptation cost than sample-wise fine-tuning.
Generating animation from a single 2D drawing is challenging because the output must preserve character appearance while remaining plausible and temporally coherent under motion. Existing drawing-based 3D animation pipelines often use sample-wise 2D refinement to align animated renderings with the input image, but such optimization tends to overfit to the observed view and fails to correct projection-induced artifacts in novel views. To address this limitation, we introduce SPECSIA-15K, a paired stylization dataset containing 14,980 artifact-corrupted projection/refinement-target pairs from 1,498 3DBiCar characters. We further present DraViE (Drawing-based View Enhancement), a lightweight plug-and-play module trained with data-level priors to remove novel-view artifacts while preserving style and motion plausibility. Experiments show consistent gains in novel-view fidelity and temporal coherence with lower per-character adaptation cost than sample-wise fine-tuning.