Variational Distribution and Experience Replay for 3D Reconstruction in a Continual Learning Framework
Published in Proceedings of the Fifteenth Indian Conference on Computer Vision Graphics and Image Processing, 2024
🏆 Best Paper Award — ICVGIP 2024
A continual learning framework for single-image 3D reconstruction that leverages variational latent priors and saliency map-based replay to preserve geometric structure and accurately reconstruct both previously seen and newly learned object classes.
Recommended citation: Sanchar Palit and Sandika Biswas, "Variational Distribution and Experience Replay for 3D Reconstruction in a Continual Learning Framework", ICVGIP, 2024.
Download Paper