正在加载视频...

视频加载失败

Most multi-view reconstruction models need full supervision. We show they can self-improve without any ground truth labels. Introducing SelfEvo: Self-Improving 4D Perception via Self-Distillation. Up to +36.5% in video depth, +20.1% in camera estimation, zero annotation.

27,348 次观看 • 7 个月前 •via X (Twitter)

7 条评论

Qianqian Wang 的头像
Qianqian Wang7 个月前

SelfEvo is driven by a very simple insight: the same model predicts better with richer context. This asymmetry creates a powerful self-distillation signal, letting the model improve itself on unlabeled data, without any additional supervision, almost like a free lunch.

Qianqian Wang 的头像
Qianqian Wang7 个月前

Despite its simplicity, SelfEvo consistently improves pretrained multi-view reconstruction models: better on new domains, no drop on original ones, with gains that transfer to unseen domains, all without ground-truth annotations.

Qianqian Wang 的头像
Qianqian Wang7 个月前

SelfEvo is flexible: it makes no static-scene assumption or multi-view consistency requirement, and significantly improves performance on dynamic scenes where annotations are most scarce. We visualize how model predictions on unseen dynamic scenes evolve during training.

Qianqian Wang 的头像
Qianqian Wang7 个月前

Project page: Code: Led by @NanHuangg and @pengcheng_147, with @WeijiaZeng1, @RehgJim, @akanazawa, and @HavenFeng

مازن وذكاء الآلات 的头像
مازن وذكاء الآلات7 个月前

Impressive gains with zero annotation. If this scales, it removes one of the biggest bottlenecks in multi view reconstruction: labeled data. Approaches like this could push 4D perception to learn directly from massive video streams.

David Nordström 的头像
David Nordström7 个月前

This feels like a great idea and potentially applicable to many problems. Have people done something similar before?

Reyansh Shirke 的头像
Reyansh Shirke2 个月前

Qian

相关视频