Winners

Vesuvius Challenge has awarded $1,868,000 in prizes since the competition started in 2023! This page lists all the prizes awarded so far.

$31,000 Progress Prizes (August 2026)

Goal: Improve the tools and training methods needed to read the scrolls.

$20,000

Patch-based unwrapping: William Stevens

Detects when the 2D alignments of overlapping patches imply incompatible 3D locations, drops the offending patches, and joins the rest into flattened components — around 365 cm² of coverage on PHerc. 1667.

$2,500

9 µm surface model & ScrollFiesta fixes: Ben Kyles / @hari_seldon and collaborators

A retrained 9 µm surface model distilled from 2.4 µm predictions, producing thinner and more continuous sheets with fewer blobs, plus bugfixes and improvements across the end-to-end ScrollFiesta unwrapping pipeline.

$1,000

Ink checkpoint benchmarking: Domenico Russo

Benchmarks all 14 released 9 µm ink checkpoints, and retrains from dense teacher labels instead of the sparse hand-labelled strips.

$1,000

Seeded sheet growing: Mihajlo Nestorović

A trained 3D model that grows a single papyrus sheet from a seed, along with a pipeline for generating harder sheet-level training data.

$1,000

How many depth slices?: Paulo Sergio Camillo / @pscamillo

Real training experiments on how many depth slices the 9 µm ink model actually needs.

$1,000

Lasagna & VC3D improvements: Santiago Pelufo

Seven merged villa changes, including Mac GPU flattening in Lasagna, a HiDPI scale bar, and assorted navigation and registration fixes.

$1,000

First Letters on PHerc. 0826: Lutfiya Miller and Chris Müller

Ran the First Letters workflow end to end on PHerc. 0826 and published the images, commands, failures and costs — with plenty of useful insight for others attempting it — plus two merged PRs.

$1,000

nnInteractive label refinement: Benjamin Hamm

Applies nnInteractive to surface label refinement, producing labels much closer to the true surface (though with some remaining topological issues).

$500

Dense pseudo-labels & checkpoint repair: Erwin Nieuwlaar

Extends the ink training recipe with dense pseudo-labels from native 113 keV scans, and repairs a published Scroll 1 checkpoint whose untrained output layer was emitting blank predictions.

$500

Assorted villa fixes: Oleksandr Kozlenko

Several useful fixes across training, inference, coordinate scaling, validation metrics and CLI tools.

$500

Sustained PR work: TAUIL Abd Elilah

PR work throughout the month, including making vesuvius.predict preprocess CT the same way the model was trained.

$250

Shared disk cache: Praneeth Reddy

Makes villa's neural-tracing disk cache available to the general model workflow, so reruns stop redownloading the same chunks.

$250

Spiral fitting on Windows: Shuhan Yang

Gets the spiral-fitting tools building and running on Windows with lower compute resources, plus patches that cut render traffic and time on remote volumes.

$250

VC3D agent bridge fixes: Ryan Gurganious

Lets VC3D's agent bridge start Lasagna with the selected volume, and download large segments without reporting them missing.

$250

Checkpoint averaging: Armando Gaona de Stefani

Careful checkpoint-averaging experiments on the ink models.

$33,500 Progress Prizes (July 2026)

Goal: Improve the tools and training methods needed to read the scrolls.

$20,000

ScrollFiesta: Ben Kyles / @hari_seldon

Continued development of the automatic surface mesher: now villa-compatible (zarr in, tifxyz out), snaps to papyrus in the CT scan, and produces constraints for spiral fitting.

$2,500

Optimising patch connectivity: William Stevens

Identifies and removes problem areas that cause sheet switching, leaving a scaffolding of known-good patches; run across all of Scroll 4.

$1,000

Portable GPU kernels for ScrollFiesta: Alan Thompson

A Rust/CubeCL driver for ScrollFiesta's MLS-midpoint projection hotspot that runs on AMD, NVIDIA, and WGPU.

$1,000

Zarr 3 read fixes: Prasad Khake

Fixes multiscale zarr 3 reads in the Python vesuvius Volume and restores an opt-in chunk cache.

$1,000

Ink detection validation harness: Hyojun Kwon

A reworked ink-detection tutorial with proper held-out validation splits, plus an upstream OOM fix.

$1,000

windcheck: Josep Carreras

Detects self-intersections in tifxyz surfaces, catching silent wrap-crossing errors for large-scale filtering.

$1,000

TIFXYZ Doctor: Aviad Cohen

A deterministic QA and triage tool for tifxyz surface grids: metadata, consistency, distortion, and topology checks, plus a merged VC3D bounds fix.

$1,000

Faster decohesion augmentation: J. Miguel Giraldo

Vectorized the DecohesionTransform training augmentation, replacing a per-iteration GPU kernel loop.

$1,000

Reproducibility fixes & ROI inference: TAUIL Abd Elilah

Assorted merged fixes and ROI inference support, plus a negative-result analysis of cross-scroll ink-signal measurement.

$1,000

Spiral fitting on consumer GPUs: Shuhan Yang

Makes the official spiral fitter run on 12 GB cards and without the native vc C++ extension.

$1,000

tifxyz repair & tracing fixes: Erwin Nieuwlaar

Fixes tifxyz meta.json bounding boxes and rescales neural-tracing displacements for non-training voxel sizes.

$1,000

scroll-data-audit: Matteo Bulloni

Defect-hunting across the open-data catalog and volume-cartographer, with catalog metadata checks and merged VC3D fixes.

$1,000

fit_spiral fixes: Nicolas Dolegieviez

Four merged fixes making fit_spiral work on Windows and turning silently zeroed losses into loud failures.

$3,000 Progress Prizes (June 2026)

Goal: Improve the tools and training methods needed to read the scrolls.
Announcement: Blog post

$2,000

3D augmentations & ScrollFiesta speedups: Paulo Sergio Camillo / @pscamillo

More CT-scan-artifact-inspired augmentations for training 3D segmentation models, plus performance improvements to ScrollFiesta.

$1,000

Fiber format converter: Joseph Balmaceda

Converts skeleton-annotated fibers from NML into CSV, JSON, and SWC, with length, branching, and orientation analysis.

$12,000 Progress Prizes (May, 2026)

Goal: Improve the tools and training methods needed to read the scrolls.
Announcement: Blog post

$10,000

Scroll Fiesta: Ben Kyles / @hari_seldon

An automatic mesher of surface predictions that attempts to fix topological mistakes.

$2,000

3D augmentations: Paulo Sergio Camillo / @pscamillo

Scroll Decohesion, Realistic Warp, and Squeeze transforms for training ML models on CT scans.

$200,000 Kaggle Surface Detection (March, 2026)

Goal: Optimize topologically accurate papyrus surface detection methods.
Announcement: Blog post / Kaggle competition / Kaggle leaderboard

$60,000

1st: Vesuvius Team

$40,000

2nd: risk of overfitting

$30,000

3rd: W & A

$20,000

4th: Starry

$15,000

5th: Dieter

$10,000

6th: #hui

$10,000

7th: DECEM

$5,000

8th: lingyundev

$5,000

9th: 阿對對對對隊

$5,000

10th: Vibes & Scrolls Trade-off

$1,000 Open Source (March, 2026)

Goal: Improve virtual unwrapping for the Surface Detection challenge.
Announcement: Blog post

$1,000

Scroll Slab Viewer: Paul Geiger / @PaulG

A user-friendly 3D viewer tailored to the Kaggle Surface Detection challenge.

$1,000 Open Source (July, 2025)

Goal: Improve virtual unwrapping
Announcement: Blog post

$1,000

Data handling and ball-spring method: William Stevens / @Will Stevens

$2,500 Open Source (June, 2025)

Goal: Improve virtual unwrapping
Announcement: Blog post

$2,500

Stress metrics: William Stevens / @Will Stevens

$7,000 Open Source (May, 2025)

Goal: Updates to tooling
Announcement: Blog post

$5,000

VC3D stability improvements: Philip Allgaier / @spacegaier

$1,000

Volume masking pipeline: Marcel Roth / @_mvrcii

$1,000

neuroglancer-mini: Hsiao Yao and Dalufish / @.yaohsiao and @dalufish

$60,000 First Title Prize (May, 2025)

Goal: Discover the end title of a sealed Herculaneum scroll.
Announcement: Blog post

$60,000

Winner: Marcel Roth and Micha Nowak

$7,000 Open Source (April, 2025)

Goal: Get us closer to reading entire scrolls
Announcement: Blog post

$2,500

Further work on ball and spring surface growing and analysis: Will Stevens

$2,500

Mask-3D fork and work on synthetic data generation: Lachlan Parker

$1,000

Surface refinement in khartes: Stephane Gouttebroze

$1,000

Simplified fork of neuroglancer: Yao Hsao

$10,500 Open Source (February, 2025)

Goal: Get us closer to reading entire scrolls.
Announcement: Blog post

$2,500

vesuvius-gui developments: Johannes Rudolph / @jrudolph

$2,500

Improved FASP segmentation: Hendrik Schilling / @waldkauz

$2,500

VC3D improvements: Hendrik Schilling / @waldkauz

$1,000

Masked scroll Zarrs: Forrest McDonald / @verditelabs

$1,000

Particle-based flattening: William Stevens / @Will Stevens

$1,000

Ink detection refinements: Hendrik Schilling / @waldkauz

$60,000 First Automated Segmentation (December, 2024)

Goal: Reproduce the 2023 Grand Prize segmentation result, but faster.
Announcement: Blog post

$30,000

Gold Aureus++: Hendrik Schilling / @waldkauz, Sean Johnson / @sean (bruniss)

$30,000

Gold Aureus++: Paul Henderson / @pmh47

$13,500 Open Source (December, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$2,500

Volumetric segmentation model: Tim Skinner / @Tim S, Lachlan Parker, John Skinner

$2,500

Ink labels: Nicola Bodill / @polytrope

$2,500

Interactive mesh refinement: James Darby / @james darby

$1,000

vesuvius-render: Johannes Rudolph / @jrudolph

$1,000

Electric field-based flattening: Yao Hsiao / @Yao Hsiao, Dalufishe / @Dalufish

$1,000

Data overlays in Khartes: Chuck / @khartes_chuck

$1,000

Optimized ink detection: Hendrik Schilling / @waldkauz

$1,000

Supervoxel-based segmentation methods: Forrest McDonald / @verditelabs

$1,000

Segmentation tools: William Stevens / @Will Stevens

$29,000 Open Source (November, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$10,000

Segment patch generation: Hendrik Schilling / @waldkauz

$10,000

vesuvius-c library: Forrest McDonald / @verditelabs

$2,500

Electric potential scroll flattening: Yao Hsiao / @Yao Hsiao, Dalufishe / @Dalufish

$2,500

Various datasets: Sean Johnson / @sean (bruniss), Hendrik Schilling / @waldkauz

$1,000

phalanx: Marcel Roth

$1,000

2D -> 3D labeling tool: James Darby / @james darby

$1,000

zarr_to_ome script: Chuck / @khartes_chuck

$1,000

New segment in title region: Elian Rafael Dal Prá / @err, Sean Johnson / @sean (bruniss)

$18,500 Open Source (October, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$2,500

Segmentation models: Sean Johnson / @sean (bruniss)

$2,500

Optimizing surface models: Hendrik Schilling / @waldkauz

$2,500

Surface mesh refinement: Hendrik Schilling / @waldkauz

$2,500

C library: Forrest McDonald / @verditelabs

$2,500

Zarr support in vesuvius-gui: Johannes Rudolph / @jrudolph

$1,000

Self-supervised pretraining for ink detection: Jorge García-Carrasco / @jgcarrasco

$1,000

Interactive segmentation improvements in Volume Cartographer: Hendrik Schilling / @waldkauz

$1,000

Segmentation toolkit improvements: William Stevens / @Will Stevens

$1,000

Umbilicus Maker: James Darby / @james darby

$1,000

Meshing high curvature segmentations: James Darby / @james darby

$1,000

Visualization canvas: Yao Hsiao / @Yao Hsiao, Dalufishe / @Dalufish

$48,500 Open Source (September, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$20,000

Fiber following: Sean Johnson / @sean (bruniss)

$10,000

Inkalyzer: Youssef Nader / @YoussefNader

$2,500

Fragment ink labeling: Youssef Nader / @YoussefNader

$2,500

Fast meshing and flattening: Hendrik Schilling / @waldkauz

$2,500

Meshes from volumetric labels: James Darby / @james darby

$2,500

vesuvius-gui improvements: Johannes Rudolph / @jrudolph

$2,500

Self-supervised ink detection: Jorge García-Carrasco / @jgcarracsco, Andoni Irazusta-Garmendia / @theleprechaun25

$1,000

Segmentation optimization: Hendrik Schilling / @waldkauz

$1,000

Volumetric labeling improvements: James Darby / @james darby

$1,000

Scroll Sleuth: Paul Geiger / @PaulG

$1,000

Small surface segmentation: William Stevens / @Will Stevens

$1,000

Data streaming in Khartes: Chuck / @khartes_chuck

$1,000

Vesuvius Ink Generator: Seth Stewart

$41,000 Open Source (August, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$10,000

Segment Browser: Johannes Rudolph / @jrudolph

$10,000

Volumetric instance labeling: James Darby / @james darby

$10,000

Khartes3D: Chuck / @khartes_chuck

$2,500

Rescaled fragment surface volumes: Johannes Rudolph / @jrudolph

$2,500

Flood fill for segmentation: Will Stevens / @Will Stevens

$2,500

Convert volumetric segmentations to meshes: James Darby / @james darby

$2,500

Ink detection patch aggregation report: Arefeh Sherafati / @arefeh, Lou Schlessinger / @ls_96

$1,000

wj-wt-ftt: Yao Hsiao / @Yao Hsiao, Dalufishe / @Dalufish

$11,000 Open Source (July, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$2,500

3D instance segmentation improvements: James Darby / @james_darby

$2,500

Vesuvius GP+: Jared Landau / @tetradrachm

$2,500

DINO ink detection: Jorge García Carrasco / @jgcarrasco

$2,500

Hraun updates: Forrest McDonald / @verditelabs

$1,000

Web volume annotator: Yao Hsiao / @Yao Hsiao, Dalufishe / @Dalufish

$12,500 Open Source (June, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$2,500

Volumetric segmentation tools: James Darby / @james_darby

$2,500

Volume Cartographer improvements: Philip Allgaier / @spacegaier

$2,500

Segmentation pipeline: Santiago Pelufo / @spelufo

$1,000

Scroll volume alignment: Paul Geiger

$1,000

Updated 3D ink detection volume: Sean Johnson / @Bruniss

$1,000

Web volume viewer: Huang Cheng Jiun / @pocper1, Yao Hsiao / @Yao Hsiao

$1,000

Seam carving for densification: James Darby / @james_darby

$1,000

Mesh chunking: James Darby / @james_darby

$29,000 Open Source (May, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$10,000

Volume Cartographer improvements: Philip Allgaier / @spacegaier

$10,000

Khartes improvements: Chuck / @khartes_chuck

$2,500

Scroll 2 segments: Sean Johnson / @Bruniss

$2,500

vesuvius-gui: Johannes Rudolph / @jrudolph

$1,000

Scroll compression and masking: Oliver Daubney / @O_D

$1,000

Volumetric segmentation architecture investigation: James Darby / @james_darby

$1,000

Browser-based scroll viewer: Yao Hsiao / @Yao Hsiao

$1,000

3D segmentation prototype: Forrest McDonald / @VerditeLabs

$35,000 Open Source (April, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$20,000

3D ink detection: Ryan Chesler / @emel_ryan

$2,500

Mesh merging: Giorgio Angelotti / @Jordi

$2,500

Instance segmentation labels: James Darby / @james darby

$2,500

Unsupervised pretraining: Ryan Chesler / @emel_ryan

$2,500

New segments: Sean Johnson / @Bruniss

$1,000

Volumetric processing tools: Forrest McDonald / @VerditeLabs

$1,000

Point cloud comparison: Giorgio Angelotti / @Jordi

$1,000

Instance segmentation experiments: James Darby, Ryan Reszetnik, Liamo Pennimpede, Lucas Nelson

$1,000

Meshing and chunking: Santiago Pelufo / @spelufo

$1,000

Pipeline Visualize: Yao Hsiao / @Yao Hsiao

$42,500 Open Source (March, 2024)

Goal: Increase the probability we read 90% of four scrolls in 2024.
Announcement: Blog post

$20,000

Rendering improvements: Giorgio Angelotti / @Jordi

$10,000

Multiresolution chunked volumes: Chuck / @khartes_chuck

$2,500

Volumetric ink detection: Jorge Villaescusa / @mojonero

$2,500

Volumetric segmentation labels: Tim Skinner / @Tim S

$2,500

Data improvements: James Darby / @james darby

$1,000

Segment-to-segment label mapping: Oliver Daubney / @O_D

$1,000

Cell viewer and segmentation comparison: Yao Hsiao / @Yao Hsiao

$1,000

Superpixels and cells: Santiago Pelufo / @spelufo

$1,000

Other segmentation axes, 3D ink labels: Sean Johnson / @Bruniss

$1,000

Colab notebook and ink labels: Nicola Bodill / @polytrope

$850,000 Grand Prize 2023 (December 31, 2023)

Goal: Reveal four passages within the scrolls.
Announcement: Announcement page

$700,000

Winner: Youssef Nader, Luke Farritor, and Julian Schilliger

$50,000

Runner up: SQ Mah

$50,000

Runner up: Lou Schlessinger and Arefeh Sherafati

$50,000

Runner up: Elian Rafael Dal Prá, Sean Johnson, Leonardo Scabini, Raí Fernando Dal Prá, João Vitor Brentigani Torezan, Daniel Baldin Franceschini, Bruno Pereira Kellm, Marcelo Soccol Gris, and Odemir Martinez Bruno

$12,000 Open Source (December 31, 2023)

Goal: Increase the probability the Grand Prize gets awarded.
Announcement: Blog post

$3,000

Segment maps by Yao Hsiao / @Yao_Hsiao

$3,000

Large segments and colab notebook by Sean Johnson / @Bruniss

$3,000

Crackle Viewer by Julian Schilliger / @RICHI

$3,000

Segment maps by Youssef Nader / @YoussefNader

$25,000 Open Source (November 30, 2023)

Goal: Increase the probability the Grand Prize gets awarded.
Announcement: Blog post

$8,000

Next-gen Volume Cartographer: Philip Allgaier / @spacegaier

$5,000

Segment Browser: Johannes Rudolph / @jrudolph

$5,000

Ink Detection Masks: Anton Repushko / @repushko

$1,000

Sharkbite fix: Chuck / @khartes_chuck

$1,000

Vesuvius Kintsugi: Giorgio Angelotti / @jordi45698

$1,000

Crackle Labels: Sean Johnson / @bruniss

$1,000

Omit: Timo Meireman / @timo_71099

$1,000

Segment Viewer by Yao Hsiao / @Yao_Hsiao and Dalufishe / @Dalufish

$1,000

Single-sheet Segmentation: Brett Olsen / @brett_olsen

$1,000

Multiple Contributions: Santiago Pelufo / @spelufo

$60,000 First Letters & Ink (October 12, 2023)

Goal: Find the first letters within the scrolls.
Announcement: Announcement page

$40,000

First Letters: Luke Farritor / @lukeboi

$10,000

First Letters, 2nd place: Youssef Nader / @YoussefNader

$10,000

First Ink: Casey Handmer / @cjhandmer

$45,000 Segmentation Tooling 2 (October 3, 2023)

Goal: Help the segmentation team do larger and harder areas.
Announcement: Blog post

$10,000

VA Sheet Tracer by Trevor, Tom, Babak, and Boaz

$10,000

Extremely Fast Segmentation by Julian Schilliger / @RICHI

$10,000

Khartes by Chuck / @khartes_chuck

$5,000

CT scanning campfire scrolls by Ahron Wayne / @WayneWayneHello

$5,000

Segment Viewer by Yao Hsiao / @Yao_Hsiao and Dalufishe / @Dalufish

$5,000

Ilastik integration by Santiago Pelufo / @spelufo

$12,000 Ink Detection Followup (September 8, 2023)

Goal: Take the models from the Ink Detection Prize (see below) and apply them to the scrolls, to find letters.
Announcement: Blog post

$3,000

Top Ink Detection Model Analysis by Ryan Chesler / @emel_ryan

$3,000

Fine Tuning by Luke Farritor / @lukeboi

$1,500

Crackle Viewer by Julian Schilliger / @RICHI

$1,500

Resolution Analysis by Team OverthINKingSegmenter

$1,500

Scroll Pretraining by Youssef Nader / @YoussefNader

$1,500

Vesuvius Challenge Whiteboard by Yao / @Yao_Hsiao and Dalufishe / @Dalufish

$45,000 Segmentation Tooling (June 27, 2023)

Goal: Help the segmentation team do larger and harder areas.
Announcement: Blog post

$10,000

Optical Flow Segmentation by Julian / @RICHI

$10,000

Khartes by Chuck / @khartes_chuck

$5,000

Masked data by James / @thatGuy

$5,000

Volume Viewer by Yao / @Yao_Hsiao

$5,000

VolumeAnnotate by Moshe / @moshelevy

$5,000

Scroll Viewer by Luke Farritor / @lukeboi

$5,000

vesuvius-build and vesuvius-blender by Santiago / @spelufo

$100,000 Kaggle Ink Detection (July 14, 2023)

Goal: Optimize fragment-based ink detection methods.
Announcement: Blog post / Kaggle competition / More info

$25,000

1st: ryches

$20,000

2nd: RTX23090

$15,000

3rd: wuyu

$10,000

4th: POSCO DX - Heeyoung Ahn

$5,000

5th: Aksell

$5,000

6th: chumajin

$5,000

7th: OverthINKingSegmenter

$5,000

8th: Luck is all you need

$5,000

9th: still 1 fold, 2 net

$5,000

10th: Feng Qilong

$10,000 Open Source (April 14, 2023)

Goal: Increase the probability the Grand Prize gets awarded.
Announcement: Blog post / Live stream

$2,500

Scroll Viewer by Luke Farritor / @lukeboi

$2,500

2.5D Segmentation Baseline by Ryosuke Tanaka

$2,500

VolumeAnnotate by Moshe Levy / @moshelevy

$2,500

Countless community contributions by Brett Olsen / @caethan

EduceLab tools

Before and during the competition, EduceLab has put out various works. With these tools, they have laid the foundation for the community. While EduceLab members are ineligible for prizes, we want to recognize their efforts.

Quick Segment by Bruno, Sydney, and Drew. © EduceLab/University of Kentucky.

Hard-Hearted Scrolls (PhD dissertation) by Stephen Parsons. © Stephen Parsons.

Volume Cartographer by Seth Parker and many others. © EduceLab/University of Kentucky.

ink-id by Stephen Parsons. © EduceLab/University of Kentucky.