Hyper-Object Challenge

Reconstructing Hyperspectral Cubes of Everyday Objects from Low-Cost Inputs

Learn More Github

About the Challenge

Hyperspectral imaging (HSI) captures fine-grained spectral information, enabling precise material analysis. However, commercial HSI cameras are expensive and bulky. In contrast, RGB cameras are affordable and ubiquitous.

The Hyper-Object Challenge aims to revolutionize access to spectral imaging by developing learning-based models that can reconstruct high-fidelity hyperspectral cubes (400-1000 nm) from low-cost inputs like mosaic sensor data or standard low-resolution RGB images. This would unlock applications from counterfeit detection to agricultural monitoring using everyday devices.

Example images from the Hyper-Object dataset

Diverse everyday objects from the Hyper-Object dataset.

Challenge Tracks

The competition comprises two distinct tracks, each defined by a different low-cost input format i_k.

Track 1: Spectral Reconstruction from Mosaic Images

Each input i_k is a mosaic image that captures only one spectral band per pixel.

\( i_k \in \mathbb{R}^{H \times W \times 1} \)

Every pixel is filtered according to a predefined tiling pattern that mimics a snapshot spectral sensor. The task is to reconstruct the full spectral cube

\( h_k \in \mathbb{R}^{H \times W \times C} \)

Objective

Recover all C = 61 spectral bands (400 – 1000 nm, 10 nm spacing) from the spectrally-subsampled observation.

Evaluation

Ranking uses the composite score that aggregates RMSE, SAM, PSNR, SSIM, and EGRAS.

Track 2: Joint Spatial and Spectral Super-Resolution

Each input i_k is a low-resolution RGB image captured by a commodity camera.

\( i_k \in \mathbb{R}^{h \times w \times 3}, \qquad h \ll H,\; w \ll W \)

The goal is to jointly recover spatial and spectral resolution by reconstructing

\( h_k \in \mathbb{R}^{H \times W \times C} \)

where C ≫ 3 and H ≫ h, W ≫ w.

Objective

Produce a high-fidelity hyperspectral cube that restores full spatial and spectral resolution.

Evaluation

Ranking uses the composite score that aggregates RMSE, SAM, PSNR, SSIM, and EGRAS.

Important Dates (Tentative)

20 August 2025

Dataset & Baseline Release

30 November 2025

Submission Deadline

07 December 2025

2-page Papers Due (by invitation)

11 January 2026

Paper Acceptance Notification

18 January 2026

Camera-ready Papers Due

How to Participate

Access Resources

Get the training data, baseline models, and evaluation scripts on our Kaggle page.

Develop Your Model

Train your learning-based model to reconstruct high-fidelity hyperspectral cubes.

Submit & Compete

Submit your predictions on the held-out test set and climb the leaderboard.

The competition will be hosted on Kaggle. Click below to go to the competition page, register your team, and get started!

Organizers

Pai Chet Ng

Singapore Institute of Technology

Konstantinos N. Plataniotis

University of Toronto

Juwei Lu

University of Toronto

Gabriel Lee Jun Rong

Singapore Institute of Technology

Malcolm Low

Singapore Institute of Technology

Nikolaos Boulgouris

Brunel University

Thirimachos Bourlai

University of Georgia

Seyed Mohammad Sheikholeslami

University of Toronto

Leaderboard

Baseline results on the public validation set.
Final ranking will use the composite score that combines RMSE, SAM, PSNR, SSIM, and EGRAS on the hidden test set.

Track 1 Track 2

Rank	Team	Composite Score	Submissions	Last Update
1 🥇	Baseline Model (MST++)	0.726	Baseline	-
2 🥈	Baseline Model (HRNet)	0.560	Baseline	-
3 🥉	Baseline Model (HSCNN+)	0.350	Baseline	-
4	Your Team	TBD	—	—

Rank	Team	Composite Score	Submissions	Last Update
1 🥇	Baseline Model (MST++)	0.705	Baseline	-
2 🥈	Baseline Model (HRNet)	0.533	Baseline	-
3 🥉	Baseline Model (HSCNN+)	0.310	Baseline	-
4	Your Team	TBD	—	—

Frequently Asked Questions

What is the goal of the Hyper-Object Challenge?

The competition pushes the frontier of low-cost hyperspectral imaging. Participants develop learning-based models that reconstruct full hyperspectral cubes (400 – 1000 nm, 61 bands) of everyday objects from inexpensive inputs such as spectral mosaics or low-resolution RGB images.

What are the two competition tracks?

• Track 1 – Spectral Reconstruction from Mosaic Images: Recover all 61 bands from a full-resolution, single-channel spectral mosaic.
• Track 2 – Joint Spatial & Spectral Super-Resolution: Recover spatial and spectral detail from a low-resolution RGB image.

How do I participate?

Register on the Kaggle competition page, download the training data, and submit your model’s predictions on the hidden test set to appear on the leaderboard. Key dates are listed in the “Important Dates” section above.

Can I use external data or pre-trained models?

Yes. External datasets and pre-trained networks are allowed, but you must disclose them in your final write-up. The organizers and their students will not compete.

Which metrics determine my score?

We compute five metrics on every test image—RMSE, SAM, PSNR, SSIM, and EGRAS. These are min-max-normalized and combined into a single composite score used for leaderboard ranking.

Is there a submission limit?

Each team may upload up to 3 final submissions. The highest composite score among them is kept for the final ranking.