扩散驱动的自我监督学习用于形状重建和姿势估计
IEEE transactions on pattern analysis and machine intelligence
|December 24, 2025
概括
本研究介绍了一种新的扩散驱动的自我监督网络,用于类别级的姿势估计和形状重建. 该方法有效地处理多对象场景,并且优于没有手动标签的现有方法.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 机器人技术 机器人技术 机器人技术
背景情况:
- 完全监督的类别级姿势估计需要昂贵的手动注释.
- 现有的自我监督方法通常依赖于合成数据或CAD模型,并且仅限于单个对象.
- 多个对象的姿势估计和形状重建仍然是具有挑战性的任务.
研究的目的:
- 开发一个以扩散驱动的自我监督网络,用于多对象形状重建和类别级别的姿势估计.
- 通过利用没有合成数据或CAD模型的形状先验来克服现有方法的局限性.
- 为了应对课内形状变化的挑战,并提高复杂场景的性能.
主要方法:
- 引入了用于SE(3) 等价姿势特征和3D尺度不变形状信息的先前知晓的金字塔3D点变压器.
- 利用点卷积层与辐射核用于姿势意识学习和图形卷积用于形状表示.
- 开发了一种包含扩散机制的预训练至精炼自主监督训练范式.
主要成果:
- 拟议的网络在自主监督的类别级定位估计中取得了最先进的性能.
- 在多个公共数据集和自定义数据集上表现优于现有的自我监督方法.
- 在多对象场景和形状重建任务中表现出有效性,超过了一些完全监督的方法.
结论:
- 扩散驱动的自我监督网络为类别级的姿势估计和形状重建提供了强大的解决方案.
- 该方法有效地利用形状先验并处理类内变化,减少对手册注释的依赖.
- 这种方法推进了计算机视觉中的自我监督学习,用于复杂的3D场景理解.
相关概念视频
02:57The Sense of Self: Reflected Self-Appraisal and Social Comparison
According to Charles Cooley, we base our image on what we think other people see (Cooley 1902). We imagine how we must appear to others, then react to this speculation. We don certain clothes, prepare our hair in a particular manner, wear makeup, use cologne, and the like—all with the notion that our presentation of ourselves is going to affect how others perceive us. We expect a certain reaction, and, if lucky, we get the one we desire and feel good about it. But more than that, Cooley...
02:05Self-Presentation: Self-Monitoring and Self-Handicapping
People can go to great lengths to protect their self-image and present themselves in ways that they want others to see them. Sociologist Erving Goffman presented the idea that a person is like an actor on a stage. Calling his theory dramaturgy, Goffman believed that we use “impression management” to present ourselves to others as we hope to be perceived. Each situation is a new scene, and individuals perform different roles depending on who is present (Goffman, 1959). Think about the way you...
01:26Modeling in Therapy
Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in situations...
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in situations...
01:29Self-Evaluation Maintenance Model
The Self-Evaluation Maintenance (SEM) model offers a psychological framework to understand how individuals’ self-esteem is influenced by the achievements of others, particularly those with whom they share close personal bonds. The SEM model operates when personal rather than social identity guides individuals. Central to this model is the notion that individuals have an inherent desire to preserve a favorable self-image, which is continuously shaped by interpersonal comparisons and...
01:17Strategies of Self-Presentation II: Self-Verification
Self-verification is a fundamental psychological drive wherein individuals seek affirmation of their self-concept from others, striving for consistency between their internal self-view and external perceptions. This drive operates even when the self-concept is negative, influencing interpersonal behavior and feedback preferences in complex and often counterintuitive ways. Unlike the self-enhancement motive, which seeks positive evaluations, self-verification prioritizes coherence and...
01:24Strategies of Self-Presentation III: Self-Monitoring
Self-monitoring is a central construct in understanding individual differences in self-presentation strategies across social contexts. It refers to how individuals observe, regulate, and control their expressive behavior and self-presentation following situational cues. Self-monitoring reflects a person's sensitivity to social appropriateness and willingness to adapt behavior to fit varying interpersonal demands.High vs. Low Self-Monitoring IndividualsIndividuals high in self-monitoring are...