AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis

Federico Lincetto, Gianluca Agresti, Mattia Rossi, Piergiorgio Sartor, Pietro Zanuttigh

ECCV 2026 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 0 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
add modality-to-luma loss (ablation)SPoILeR FT · Mono, RGB-only FTPSNR: 21.04 -> 25.78Improved
add modality-to-luma loss (ablation)SPoILeR FT · NIR, RGB-only FTPSNR: 22.91 -> 26.55Improved
add modality-to-luma loss (ablation)SPoILeR FT · MS, RGB-only FTPSNR: 25.36 -> 25.45No clear effect
add latent space geometry loss (ablation)SPoILeR FT · MS, RGB-only FTPSNR: 23.14 -> 25.45Improved
add latent space geometry loss (ablation)SPoILeR FT · Pol, RGB-only FTPSNR: 23.08 -> 24.25Improved
add latent space geometry loss (ablation)SPoILeR FT · RGB, RGB-only FTPSNR: 29.90 -> 30.07No clear effect
add inverse function loss (ablation)SPoILeR FT · NIR, RGB-only FTPSNR: 25.96 -> 26.55Improved
add inverse function loss (ablation)SPoILeR FT · MS, RGB-only FTPSNR: 25.28 -> 25.45No clear effect
multi-scene pre-training then RGB-only fine-tuning vs training MMS-FW from scratchSPoILeR · MMS-DATA RGBPSNR: 29.53 -> 30.07Improved
use SPoILeR pre-training instead of MMS-FW with one extra MS/Pol/NIR frameSPoILeR · MMS-DATA unbalanced modalities, 1 framePSNR: gains of ~8, ~7, and ~6 dBImproved
use SPoILeR with 10 extra second-modality framesSPoILeR · MMS-DATA unbalanced modalities, 10 framesPSNR: ~2.5 dB on averageImproved
render MS directly instead of converting RGB with MST++ then training MMS-FWSPoILeR · MS renderingPSNR: 21.99 -> 25.45Improved

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