{"ID":5551863,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T06:25:51.571775532Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00525","arxiv_id":"2607.00525","title":"SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animation","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.00525","url_pdf":"https://arxiv.org/pdf/2607.00525v1","authors":"[\"Kyuwon Kim\",\"Sunjae Yoon\",\"Chang D. Yoo\"]","published":"2026-07-01T07:14:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}