MELON: reconstructing 3D objects from unposed images using a lightweight CNN and modulo loss
Google Research presents MELON (Modulo Equivalent Latent Optimization of NeRF), a method spotlighted at 3DV 2024 that jointly infers object-centric camera poses from scratch and reconstructs a NeRF from as few as 4–6 unposed images. MELON uses a tiny CNN (initialized from noise, no pre-training) to regress poses and a modulo loss that accounts for object pseudo-symmetries, integrating both into standard NeRF training to achieve state-of-the-art accuracy without initial pose estimates or complex GAN/pretraining schemes.