17 papers
PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation
Zhiyuan Yuan, Guanying Chen, Lingteng Qiu +3
Recent monocular depth estimators achieve strong zero-shot generalization, yet often struggle to preserve fine-grained structures and object boundaries. We attribute this limitatio…
Towards Consistent Video Geometry Estimation
Zhu Yu, Jingnan Gao, Runmin Zhang +9
ViGeo is a transformer-based model that estimates dense, temporally consistent geometry (depth, surface normals, and point maps) from video sequences using dynamic chunking attenti…
Glob3R: Global Structure-from-Motion with 3D Foundation Models
Junyuan Deng, Heng Li, Kejie Qiu +7
Recent 3D geometric foundation models, such as VGGT, provide robust feed-forward 3D reconstruction by directly predicting camera poses and 3D scene points from input images. Howeve…
PointSplat: Compact Gaussian Splatting via Human-Centric Prediction
Yujie Guo, Yudong Jin, Lingteng Qiu +7
Producing 3D human representations from input views on the fly is essential for immersive live streaming systems, where representation compactness is as critical as high fidelity g…
Large Depth Completion Model from Sparse Observations
Zhu Yu, Zhengyi Zhao, Runmin Zhang +7
This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without rely…
PartNerFace: Part-based Neural Radiance Fields for Animatable Facial Avatar Reconstruction
Xianggang Yu, Lingteng Qiu, Xiaohang Ren +4
We present PartNerFace, a part-based neural radiance fields approach, for reconstructing animatable facial avatar from monocular RGB videos. Existing solutions either simply condit…