AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion

Fabian Duffhauss, Ngo Anh Vien, Hanna Ziesche, Gerhard Neumann

ECCV 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Regularizing VAE latent information · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use posterior q(y) conditioned only on the target instead of q(x,y) (ablation)FusionVAE · FusionCelebA (avg)NLL avg: 237.0 -> 233.9Improved
use posterior q(y) conditioned only on the target instead of q(x,y) (ablation)FusionVAE · FusionCelebA (avg)MSE_min avg: 2.04 -> 1.93Improved
use posterior q(x,y) instead of q(y) (ablation)FusionVAE · FusionCelebA (3 inputs)NLL: 228.7 -> 180.5Mixed
max aggregation instead of Bayesian aggregation (added) (ablation)FusionVAE · FusionCelebA (avg)NLL avg: 462.6 -> 233.9Improved
max aggregation instead of Bayesian aggregation (added) (ablation)FusionVAE · FusionCelebA (avg)MSE_min avg: 5.36 -> 1.93Improved
max aggregation instead of mean aggregation (added) (ablation)FusionVAE · FusionCelebA (avg)NLL avg: 231.3 -> 233.9No clear effect
add encoder features to decoder features instead of aggregating all features (max) (ablation)FusionVAE · FusionCelebA (avg)MSE_min avg: 3.03 -> 1.93Improved
add encoder features to decoder features instead of aggregating all features (max) (ablation)FusionVAE · FusionCelebA (avg)NLL avg: 230.6 -> 233.9No clear effect
add encoder features to decoder features instead of aggregating all features (mean) (ablation)FusionVAE · FusionCelebA (avg)MSE_min avg: 2.81 -> 1.98Improved
use FusionVAE instead of CVAE with skip connectionsCVAE+S · FusionCelebA (avg)NLL avg: 308.3 -> 233.9Improved
use FusionVAE instead of CVAECVAE · FusionMNIST (avg)MSE_min avg: 1.93 -> 1.45Improved
use FusionVAE instead of CVAE+SCVAE+S · FusionMNIST (3 inputs)NLL: 12.30 -> 13.48Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy