深層ステレオモデルは形状事前分布を学習するか?
Do Deep Stereo Models Learn Shape Priors?
局所的な手がかりが弱い場合に深層ステレオモデルが単純な形状事前分布に沿った境界を出せるかを合成データで検証し、境界誤差が残ることを示した上で、視差と境界距離場を同時予測する生成モデルを提案して境界定位を改善した。
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: Linbo Tang, Aneel Damaraju, Todd Zickler
分類: cs.CV
原文アブストラクト
Localizing object boundaries is important for embodied visual systems, since small boundary errors can change the inferred geometry of physical surfaces. We study whether deep stereo models produce boundaries consistent with simple shape priors when local image and disparity cues are weak. We create a synthetic stereo dataset consisting of objects drawn from a highly constrained family of shapes, with randomized depth, slant, color and texture. Despite the simplicity of this shape space, we find that several state-of-the-art stereo models retain systematic boundary errors, even when finetuned or trained from scratch on the dataset. We then introduce a simple generative stereo model that jointly predicts disparity and a distance field representing object boundaries. The model improves boundary localization and produces contours that adhere more closely to the underlying shape space. These results expose limitations in the boundary predictions of current stereo architectures when local evidence is weak, and motivate further study of whether generative models can better combine regional grouping evidence with global geometric structure.
