IEEE ICME 2026 Grand Challenge
DyGS-Bench: Dynamic Gaussian Splatting Compression
Important Dates
2026.02.05
Starter kit + baseline + dataset release (scripts, format checks)
2026.04.07
Stage 1 Deadline
2026.04.07
Stage 2 Start
2026.04.25
Final submission deadline
2026.05.01
Results announcement
Important Notice for Stage 2
Stage 2 invitations have been sent to qualified teams.
Due to Kaggle messaging limitations, some invited teams may not have received the notification successfully.
    If your team is qualified for Stage 2 but has not received the invitation email, please contact us as soon as possible.
Contact email:
dream18455215141@163.com
In your email, please include your
team name
.
Challenge Overview
Dynamic 3D Gaussian Splatting (DyGS) enables real-time, high-fidelity rendering of dynamic scenes and is increasingly used in AR/VR/XR and volumetric video. However, naively storing a time-varying set of Gaussian primitives leads to prohibitive storage and bandwidth costs. While many compression approaches have been proposed, progress is slowed by the lack of a standardized benchmark that evaluates
rate
,
rendering quality
, and
online decoding cost
under a unified protocol.
DyGS-Bench
focuses on a realistic deployment setting where only the reconstructed
native Gaussian sequence
is available (no original multi-view training images/videos). The goal of this Grand Challenge is to advance practical codecs that compress dynamic Gaussian assets into a compact bitstream and reconstruct renderable Gaussians efficiently.
Task
Given a native dynamic Gaussian sequence {G_t} and a fixed camera set C, design an
encoder
(offline) and
decoder
(online, measured) that:
Produces a compact
bitstream
from {G_t} (offline encoding is not time-constrained).
Determine code stream size for coded Gaussian.
Achieves high rendering quality when rendering and temporal consistency Ghat_t under C compared with renderings of {G_t}.
Organizers
Name:
Chao Wang
Affiliation:
Pengcheng Lab
Email:
winchao1984@gmail.com
Name:
Xiang Li
Affiliation:
Peking University
Email:
lx1906815508@gmail.com
Name:
Jiayu Yang
Affiliation:
Pengcheng Lab
Email:
jiayuyang@pku.edu.cn
Name:
Jiahao Wu
Affiliation:
Peking University
Email:
23011212750@stu.pku.edu.cn
Name:
Jie Liang
Affiliation:
Peking University
Email:
liangjie.victor@gmail.com
Name:
Ronggang Wang
Affiliation:
Peking University
Email:
rgwang@pkusz.edu.cn