14 lines
567 B
Markdown
14 lines
567 B
Markdown
# CSE5519 Advances in Computer Vision (Topic G: 2025: Correspondence Estimation and Structure from Motion)
|
|
|
|
## MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
|
|
|
|
[link to paper](https://arxiv.org/pdf/2412.04463)
|
|
|
|
- vanilla Droid-SLAM
|
|
- mono-depth initialization
|
|
- objective movement map prediction
|
|
- two-stage training scheme
|
|
|
|
> [!TIP]
|
|
>
|
|
> How does the two-stage training scheme help with the robustness of the model? For me, it seems that this paper is just the integration of GeoNet (separated pose and depth) with full regression. |