自己教師あり深度推定における物体境界の先鋭化
Towards Sharper Object Boundaries in Self-Supervised Depth Estimation
各ピクセルの深度を混合分布としてモデル化し、自己教師あり学習のみで物体境界の深度不連続を鮮明にする手法を提案。KITTI等で境界の鋭さを最大35%改善。
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: Aurélien Cecille, Stefan Duffner, Franck Davoine, Rémi Agier, Thibault Neveu
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Accurate monocular depth estimation is crucial for 3D scene understanding, but existing methods often blur depth at object boundaries, introducing spurious intermediate 3D points. While achieving sharp edges usually requires very fine-grained supervision, our method produces crisp depth discontinuities using only self-supervision. Specifically, we model per-pixel depth as a mixture distribution, capturing multiple plausible depths and shifting uncertainty from direct regression to the mixture weights. This formulation integrates seamlessly into existing pipelines via variance-aware loss functions and uncertainty propagation. Extensive evaluations on KITTI and VKITTIv2 show that our method achieves up to 35% higher boundary sharpness and improves point cloud quality compared to state-of-the-art baselines.
