How does one keep track? The monodepth/tracking field these days:

Align3R: estimates camera poses and consistent depth maps from monocular videos.

Combining it with trackers like Cotracker3 or SAM2 could unlock many fun applications! (cf: VideoDoodles by Yu & al)

Project page (with demo): igl-hkust.github.io/Align3R.gith...
Code: github.com/jiah-cloud/A...

Resemble Enhance seems pretty good: github.com/resemble-ai/...

SAMURAI: improve the tracking robustness of SAM2 with 2 main contributions:
- adding motion information to the mask selection
- curating the memory bank based on motion cues

Project: yangchris11.github.io/samurai
Code: github.com/yangchris11/...
Paper: arxiv.org/abs/2411.11922

Pyramid Flow is quite impressive for img2video, given than it was only trained on public datasets. Clearly not as dynamic and stable as commercial solutions, but the gap seems to be closing github.com/jy0205/Pyram...

Very cool idea for working with videos and transformers: remove duplicate patches and add length embeddings instead. They get a 40% speedup finetuning Vit-L using example packing.

Run-Length Tokenization (NeurIPS 2024 spotlight):
Project: rccchoudhury.github.io/rlt
Code: github.com/rccchoudhury...