CV

This category is about Computer Vision

Mastering the Motion: My Deep Dive into Deformable Neural Radiance Fields (D-NeRF)

by

One of the most frustrating limits of early Neural Radiance Fields (NeRF) was their “statue-like” nature. They were great for static objects, but as soon as something moved, the math broke. Recently, I’ve been obsessed with the paper “Unlocking Dynamic Scene Understanding: Neural Radiance Fields for Deformable Objects.” The premise is brilliant: instead of just mapping coordinates (x,y,z) to … Read more

Beyond the Frame: How I Reproduced SceneCompleter for 3D Scene Generation on My Local Rig

by

There is a recurring “wall” every AI hobbyist hits when working with Novel View Synthesis (NVS). You generate a beautiful second view of a room, but as soon as you try to “walk” further into the scene, the geometry falls apart like a house of cards. Recently, I came across the paper “SceneCompleter: Dense 3D Scene … Read more