Home  | News

26.10.2025

Tiny logo
Teaser image to CSG-Fusion Wins Best Paper at ICCV 2025 Workshop

CSG-Fusion Wins Best Paper at ICCV 2025 Workshop

Award-Winning Work by MCML Director Daniel Cremers and Junior Members Wenbo Ji and Weirong Chen

The paper “CSG-Fusion: Consistent Sparse-View Gaussian Splatting via Matching-based Fusion” by MCML Director Daniel Cremers and Junior Member Weirong Chen, together with Wenbo Ji, and Yan Xia, received the Best Paper Award at the ICCV 2025 Workshop on End-to-End 3D Learning.

CSG-Fusion reduces redundant Gaussian representations in pixel-aligned pointmaps for compact, consistent 3D reconstructions using a matching prior, mask-based feature aggregation, and context-view supervision.

Congratulations to the team on this outstanding achievement!

Check out the full paper:

Y. Xia • W. Ji • W. ChenD. Cremers
CSG-Fusion: Consistent Sparse-View Gaussian Splatting via Matching-based Fusion.
E2E3D @ICCV 2025 - Workshop on End-to-End 3D Learning at the IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai’i, Oct 19-23, 2025. Best Paper Award. DOI

 

#award #research #cremers

Related

Link to MCML at CHI 2026

10.04.2026

MCML at CHI 2026

MCML researchers are represented with 6 papers at CHI 2026.

Read more
Link to MCML at ICPC 2026

10.04.2026

MCML at ICPC 2026

MCML researchers are represented with 1 paper at ICPC 2026.

Read more
Link to Nikita Araslanov Receives Prestigious Emmy Noether Grant

09.04.2026

Nikita Araslanov Receives Prestigious Emmy Noether Grant

Nikita Araslanov, MCML Junior Member, awarded Emmy Noether Grant to establish an independent AI research group at TUM.

Read more
Link to How AI Avatars Shape Perceived Fairness

02.04.2026

How AI Avatars Shape Perceived Fairness

Accepted at CHI 2026, this study shows how the race and gender of AI interview avatars shape perceptions of fairness and bias in automated hiring.

Read more
Link to GRaM Competition @ ICLR 2026

31.03.2026

GRaM Competition @ ICLR 2026

GRaM Competition 2026 challenges participants to predict airflow dynamics using AI on 3D geometries. Deadline: April 22 (AoE).

Read more
Back to Top