Episode
SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
- Podcast
- Daily Paper Cast
- Published
- Jun 11, 2026
- Duration seconds
- 1321
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/47d67499
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/scail-2-unifying-controlled-character-animation-with-end-to-end-in-context-conditioning/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/scail-2-unifying-controlled-character-animation-with-end-to-end-in-context-conditioning.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
š¤ Upvotes: 32 | cs.CV Authors: Wenhao Yan, Fengjia Guo, Zhuoyi Yang, Jie Tang Title: SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning Arxiv: http://arxiv.org/abs/2606.10804v2 Abstract: Controlled character animation requires transferring motion from a driving sequence to a reference character. Prior works heavily rely on intermediate representations, including pose skeletons to represent motion or masked background to represent environment, which inevitably leads to information loss. To address this, we present SCAIL-2, a framework that bypasses those intermediates and achieves \textbf{end-to-end} character animation. By directly concatenating driving videos to the sequence, the model can obtain all the required visual information from the input video. To address the lack of end-to-end data, we unify sub-tasks of character animation with decoupled conditions and then curate a pipeline to synthesize MotionPair-60K, an end-to-end motion transfer dataset containing heterogeneous tasks of character animation. To achieve the unification, we utilize in-context mask conditioning and mode-specific RoPE as soft guidance beyond textual instructions and raw visual information. To address synthetic discrepancy in detailed regions, we propose Bias-Aware DPO to construct preference items to mitigate the errors. Extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches in various character animation tasks. A large subset of synthetic data as well as model weights will be released at our project page: https://teal024.github.io/SCAIL-2/.