IEEE ICME 2026 Grand Challenge
DyGS-Bench Evaluation
What is evaluated?
Submissions are evaluated by comparing your rendered images with hidden GT images under the same views:
Quality
: image-to-image metrics on aligned frames/cameras.
Image submission track (current)
For online testing convenience, this Codabench bundle currently evaluates an
image submission track
:
participants upload their locally rendered test-view images. The scorer compares them against hidden GT images.
Metrics
PSNR
(higher is better)
SSIM
(higher is better)
Submission Package (template)
Unless otherwise stated, please prepare a single zip file with the following structure:
<scene_name>/
  frame000000/
    images/
      cam00.png
      cam01.png
      ...
  frame000001/
    images/
      cam00.png
    ...
readme.txt (optional)
Note:
Your submission must contain the required images for each GT frame/camera you want to be evaluated on.
How Codabench runs your submission
Codabench typically executes two steps:
Ingestion
: copies your submission into the scoring input folder.
Scoring
: compares your uploaded images with hidden GT images and writes
scores.json
.
Baseline
Baseline results (representative dynamic reconstruction methods) will be provided in the starter kit, together with scripts for rendering and metric computation.
Contact
For questions about evaluation rules or submission formatting, please contact the organizers listed on the Organizers page.