Songyou Peng
songyoupeng.bsky.social
Songyou Peng
@songyoupeng.bsky.social
270 followers 72 following 4 posts
Google DeepMind. PhD from ETH Zurich & MPI-IS. https://pengsongyou.github.io/
Posts Media Videos Starter Packs
Reposted by Songyou Peng
Your personalized CVPR 25 @cvprconference.bsky.social conference programs are now available for you!
www.scholar-inbox.com/conference/c...
Reposted by Songyou Peng
Excited to present our #CVPR2025 paper DepthSplat next week!
DepthSplat is a feed-forward model that achieves high-quality Gaussian reconstruction and view synthesis in just 0.6 seconds.
Looking forward to great conversations at the conference!
🏠 Introducing DepthSplat: a framework that connects Gaussian splatting with single- and multi-view depth estimation. This enables robust depth modeling and high-quality view synthesis with state-of-the-art results on ScanNet, RealEstate10K, and DL3DV.
🔗 haofeixu.github.io/depthsplat/
Reposted by Songyou Peng
🏠 Introducing DepthSplat: a framework that connects Gaussian splatting with single- and multi-view depth estimation. This enables robust depth modeling and high-quality view synthesis with state-of-the-art results on ScanNet, RealEstate10K, and DL3DV.
🔗 haofeixu.github.io/depthsplat/
Super excited to share Visual Chronicles! Huge kudos to @boyangdeng.bsky.social on his fantastic internship work with us at Google DeepMind. It was one of the coolest and most fun projects I've ever been a part of!

Tell us what trends we discovered surprise you: boyangdeng.com/visual-chron...
Desired for accurate camera poses for long sequences in dynamic scenes, and also dense 3D reconstruction?

Check out our #CVPR25 paper WildGS-SLAM – bridging robust SLAM and high-fidelity 3D Gaussians in the wild!
🥳Excited to share our latest work, WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments, accepted to #CVPR2025 🌐

We present a robust monocular RGB SLAM system that uses uncertainty-aware tracking and mapping to handle dynamic scenes.
Reposted by Songyou Peng
Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views

Chong Bao, Xiyu Zhang, Zehao Yu, Jiale Shi, Guofeng Zhang, @songyoupeng.bsky.social, Zhaopeng Cui

tl;dr: DUSt3R+layered GS+video diffusion model

arxiv.org/abs/2503.24382
Reposted by Songyou Peng
🚀 Names matter! We show that better class names in open-vocabulary segmentation benchmarks greatly improve dataset quality and boost model performance. RENOVATE your dataset labels with our automatic framework! #AI #ComputerVision #NeurIPS24
andrehuang.github.io/renovate/
Reposted by Songyou Peng
I have switched from X and Facebook to Bluesky. I will delete both my X and Facebook accounts in a little bit.
Thanks Michael for sharing! @chrisoffner3d.bsky.social would be great if you could kindly add me to the list, since I am also working on 3D Vision!