2 papers
cs.CV2025
SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
Jiaxin Guo, Tongfan Guan, Wenzhen Dong +5
Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel G…
cs.CV2025
BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment
Tongfan Guan, Jiaxin Guo, Chen Wang +1
Monocular and stereo depth estimation offer complementary strengths: monocular methods capture rich contextual priors but lack geometric precision, while stereo approaches leverage…