スペクトルステアリング:凍結拡散生成器のための局所逆幾何
Spectral Steering: Local Inverse Geometry for Frozen Diffusion Generators
凍結した拡散生成器に対し、特定の出力特性を保ちながら他の特性を変更する構造的リクエストを忠実に実現するため、リクエスト依存の余弦ゲイン予測と減衰付き逆補正を組み合わせた手法を提案し、画像・音声・ロボティクス・制御計画で有効性を示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Angelo Moroncelli, Alessandro Leanza, Loris Roveda
分類: cs.LG, cs.AI, cs.CV, cs.RO
原文アブストラクト
A frozen diffusion generator may need to change several output properties while preserving others. We study when guidance faithfully realizes such a structured request and whether local inverse correction improves its direction. Our account links this benefit to the interaction between the request and the objective-specific remaining-sampler Jacobian: conditioning alone is insufficient. Spectral steering combines a request-specific cosine-gain predictor with damped inverse correction and fixed-time relinearization for finite edits. Scalar nulls and matched-movement controls test the predicted mechanism. Across 8,923 instances in a retrospectively identified local regime, predicted and realized gains correlate at Spearman 0.79, versus -0.11 for condition number. Experiments span images, audio, robotics, and control and planning, including complex character motion generation. On 50 paired inpainting cases, four corrections improve unobserved-pixel PSNR over Adam by 3.25 dB at equal total derivative traversals. Together, the analysis and controls connect request-dependent geometry to directional gains and establish where these gains translate into downstream performance.
