Search Results for author:
Found 7 papers, 1 papers with code
Diffusion Models Trained with Large Data Are Transferable Visual Models
We show that, simply initializing image understanding models using a pre-trained UNet (or transformer) of diffusion models, it is possible to achieve remarkable transferable performance on fundamental vision perception tasks using a moderate amount of target data (even synthetic data only), including monocular depth, surface normal, image segmentation, matting, human pose estimation, among virtually many others.
Improving Neural Indoor Surface Reconstruction with Mask-Guided Adaptive Consistency Constraints
3D scene reconstruction from 2D images has been a long-standing task.
FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models
3D scene reconstruction is a long-standing vision task.
The Second Monocular Depth Estimation Challenge
This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC).
Towards Domain-agnostic Depth Completion
Our method leverages a data-driven prior in the form of a single image depth prediction network trained on large-scale datasets, the output of which is used as an input to our model.
Exploiting Correspondences with All-pairs Correlations for Multi-view Depth Estimation
However, multi-view depth estimation is fundamentally a correspondence-based optimization problem, but previous learning-based methods mainly rely on predefined depth hypotheses to build correspondence as the cost volume and implicitly regularize it to fit depth prediction, deviating from the essence of iterative optimization based on stereo correspondence.
Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth
However, in some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency.
