Paper Detail

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

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

arxiv Score 7.6

Published 2026-07-02 · First seen 2026-07-03

General AI

Abstract

Neural rendering techniques allow for accurate reconstruction of the geometry and color appearance of 3D scenes. Some methods have extended their use to additional imaging modalities, such as multispectral, infrared, or polarimetric data. However, all of these approaches require expensive sensors and calibrated setups to capture new multimodal frames for each new scene. We propose Spectral and Polarimetric Implicit Learned Representation (SPoILeR), a novel method to obtain multi-view consistent renderings of unconventional modalities for scenes where either only RGB frames or very few of the additional modalities are available. Thanks to a multimodal pre-training phase, the model learns the mutual correlation between different modalities. This step allows predicting accurate renderings of unconventional modalities during a fine-tuning phase supervised only by RGB images. Experimental results show that the approach can accurately render infrared, polarimetric, and multispectral frames for scenes where no input sample captured by these types of sensors is provided.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{lincetto2026learning,
  title = {Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesis},
  author = {Federico Lincetto and Gianluca Agresti and Mattia Rossi and Piergiorgio Sartor and Pietro Zanuttigh},
  year = {2026},
  abstract = {Neural rendering techniques allow for accurate reconstruction of the geometry and color appearance of 3D scenes. Some methods have extended their use to additional imaging modalities, such as multispectral, infrared, or polarimetric data. However, all of these approaches require expensive sensors and calibrated setups to capture new multimodal frames for each new scene. We propose Spectral and Polarimetric Implicit Learned Representation (SPoILeR), a novel method to obtain multi-view consistent },
  url = {https://arxiv.org/abs/2607.02372},
  keywords = {cs.CV},
  eprint = {2607.02372},
  archiveprefix = {arXiv},
}

Metadata

{}