My entry for the @dev.to CSS Art challenge is taking shape...
24.07.2025 12:14 β π 64 π 6 π¬ 11 π 0My entry for the @dev.to CSS Art challenge is taking shape...
24.07.2025 12:14 β π 64 π 6 π¬ 11 π 0I agree - setting up an environment is so painful and while claude/gpt/etc are okay at helping dependency issues if codex can automate this it will be so nice
17.05.2025 17:49 β π 0 π 0 π¬ 0 π 0
A thread of thoughts on radiance fields, from my keynote at 3DV:
Radiance fields have had 3 distinct generations. First was NeRF: just posenc and a tiny MLP. This was slow to train but worked really well, and it was unusually compressed --- The NeRF was smaller than the images.
looks very cool! am excited to compare this to megasam
02.04.2025 02:39 β π 2 π 0 π¬ 0 π 0okay I fell for this and now Iβm saving this monumental piece of work πππβ οΈβ οΈβ οΈ
01.04.2025 14:47 β π 0 π 0 π¬ 0 π 0
ahh this is my mistake - it is just image, pointmap datapoints
I am still impressed by soraβs ability to learn 3D without 3d info (like pointmaps)!
iβm not gonna lie the naming is hilarious ππβ οΈ alligator va croco
11.03.2025 13:49 β π 0 π 0 π¬ 0 π 0post submission cycling is like mcdonalds sprite after a hangover
11.03.2025 13:44 β π 1 π 0 π¬ 0 π 0
Iβm honestly still shocked at this - how did Sora manage to learn 3D consistency just from videos?
Dust3r (i know itβs completely different) had to be given camera parameters during its training process, so to me it makes sense it was able to understand 3D very well
if you have a CUDA machine, you can try nerfstudioβs splatfacto method if you want a video of the optimization process on custom data
there are some good videos on the nerfstudio documentation website too!
docs.nerf.studio/nerfology/me...
Gave #uv a try for managing my #python dependencies. This missing feature is quite important for my flow hence a deal breaker:
github.com/astral-sh/uv...
Following the GitHub issue to revisit when resolved but till then #nix + #poetry > #uv
the way cameraHMR managed to get the hands flat for the handstand picture was very neat!!
30.01.2025 19:31 β π 1 π 0 π¬ 1 π 0