Xiaoyang Guo

PhD@MMLAB CUHK, 3D Reconstruction, NeRF, GS, Autonomous Driving #

[Sida Peng @pengsida]

Want to reconstruct very large-scale scenes accurately?
Check out our Scal3R (CVPR'26 Highlight) — scaling up VGGT with TTT Layers: Split image sequences into chunks, compute TTT gradients per chunk, and then average gradients across chunks.
Code is out: https://t.co/KkiB4lV8CF.

[Xiaoyang Guo @gingertata]

Congratulations to Yubin and Kairui! To address the lack of precise geometric evaluation data in large-scale urban scene reconstruction, we propose the synthetic dataset SS3DM for 3D surface reconstruction of street scenes.