Stefano Gasperini

PhD Candidate in Reliable Scene Understanding @TU_Muenchen | 3D Computer Vision

[Stefano Gasperini @ste_gasperini]

I'm honored to be selected as Outstanding Reviewer at #CVPR2025!! Thanks a lot for recognizing my contribution

[#CVPR2026 @CVPR]

Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers!

https://t.co/z8w4YJKTep

[MrNeRF @janusch_patas]

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians

Contributions:
• We propose SuperGSeg: a 3D segmentation method with neural Gaussians, designed to learn hierarchical instance segmentation features from 2D foundation models.

• We introduce the concept of Super-Gaussian, a novel representation that integrates hierarchical instance segmentation features, enabling the embedding of high-dimensional language features. This approach addresses previously unfeasible challenges in representing complex scenes with rich semantic details.

• Extensive experiments on the LERF-OVS and ScanNet datasets demonstrate the effectiveness of the proposed method, achieving significant improvements in open-vocabulary 3D object-level and scene-level semantic segmentation. It shows particular strength in capturing fine-grained scene details and dense pixel semantic segmentation tasks for the first time.

[Zhenjun Zhao @zhenjun_zhao]

Re-Nerfing: Enforcing Geometric Constraints on Neural Radiance Fields through Novel Views Synthesis

Felix Tristram, Stefano Gasperini, @fedassa, Nassir Navab, @BusamBenjamin

tl;dr: first trained NeRF->pseudo-views+original views->second NeRF

https://t.co/MhwN5VceBf

[Stefano Gasperini @ste_gasperini]

I had a great time at #iccv2023 presenting 2 papers! 🎉
> mono depth in adverse conditions + code: https://t.co/9nVGJTEwft
> segmentation of known and completely unknown objects: https://t.co/TXe5eForGG
I really appreciated meeting so many people and look forward to the next one!

[Stefano Gasperini @ste_gasperini]

I am honored to be recognized as an outstanding reviewer at #ICCV2023!

[#ICCV2025 @ICCVConference]

HUGE thank you for your service to our #ICCV2023 outstanding reviewers!

[Federico Tombari @fedassa]

Excited about the work we'll present at #ICCV2023 on "Robust monocular depth estimation under challenging conditions". A simple but effective way to deal with various weather/illumination conditions, applicable to most depth ML solutions in AD and beyond: https://t.co/95gfoJrsHp