
Honorable Mentions👏
The research was co-authored with Oxford and UCL.
Positive users congratulate the DeepMind D4RT team on winning CVPR's best paper award for 4D scene reconstruction as a well-deserved contribution, while negative users criticize the work for lacking code release and reproducibility.

Honorable Mentions👏

Finalists 👏

@WenCabrel_ @pesarlin there are ways to anonymize code repositories before publicly release it after acceptance, but that's not the issue here. The paper is now accepted with a project page and blog post, but still no code.

@pesarlin They have a really fancy project page though, what more could you want?

@pesarlin Technically, I like the paper, the idea and results are super promising. I also tried to reproduce it (without using a coding agent), but the paper really lacks of enough details to reproduce😅

Best Student Paper & Honorable Mention

If I remember correctly, it was a double-blind review process, so authors should not have added their repo or anything else that would allow reviewers to identify the paper as theirs. I am sure this was done to eliminate favoritism. Once your paper is accepted, you can disclose anything—the code and so on.

@pesarlin 100%, reproducibility should be a requirement. Unofficial open-source implementation: https://github.com/Lijiaxin0111/Open-d4rt

@ChuhanZhang5 This is so cool!

@pesarlin isnt it normal to not have code released yet when submitting to confs, esp double blind submissions

Thanks to our committee members

@Parskatt @pesarlin I think Paul's point is super valid. It's authors duty to ensure your work is reproducible. If all papers propose excellent ideas and claim SOTA performance but with non-reproducible details, how can the area progress so fast?

@pesarlin how can we know if anything in this paper real, if we are unable to reprod? difference between science and product gets blurrier every day

@ChuhanZhang5 congrats!!!

@georgiagkioxari 🐐

@pesarlin When >30k papers are submitted at any AI conf, having a code should be mandatory

@georgiagkioxari a legend doesn’t need to be on social media for socials

@ChuhanZhang5 congrats, great work! are you planning on releasing the code? :)

@georgiagkioxari Kaiming he is a legend

@ChuhanZhang5 Congrats!