Details

Autor(en) / Beteiligte

• Bao, Zhipeng
• Tokmakov, Pavel
• Jabri, Allan
• Wang, Yu-Xiong
• Gaidon, Adrien
• Hebert, Martial

Titel

Discovering Objects that Can Move

Ist Teil von

• 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, p.11779-11788

Ort / Verlag

IEEE

Erscheinungsjahr

2022

Quelle

IEEE Xplore

Beschreibungen/Notizen

• This paper studies the problem of object discovery - separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. However, by relying on appearance alone, these methods fail to separate objects from the background in cluttered scenes. This is a fundamental limitation since the definition of an object is inherently ambiguous and context-dependent. To resolve this ambiguity, we choose to focus on dynamic objects - entities that can move independently in the world. We then scale the recent auto-encoder based frameworks for unsuper-vised object discovery from toy synthetic images to complex real-world scenes. To this end, we simplify their architecture, and augment the resulting model with a weak learning signal from general motion segmentation algorithms. Our experiments demonstrate that, despite only capturing a small subset of the objects that move, this signal is enough to generalize to segment both moving and static instances of dynamic objects. We show that our model scales to a newly collected, photo- realistic synthetic dataset with street driving scenarios. Additionally, we leverage ground truth segmentation and flow annotations in this dataset for thorough ablation and evaluation. Finally, our experiments on the real-world KITTI benchmark demonstrate that the proposed approach outperforms both heuristic- and learning-based methods by capitalizing on motion cues.