Depthcrafter: Generating consistent long depth sequences for open-world videos

W Hu, X Gao, X Li, S Zhao, X Cun, Y Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
Despite significant advancements in monocular depth estimation for static images,
estimating video depth in the open world remains challenging, since open-world videos are …

Masked modeling for self-supervised representation learning on vision and beyond

S Li, L Zhang, Z Wang, D Wu, L Wu, Z Liu, J **a… - arxiv preprint arxiv …, 2023 - arxiv.org
As the deep learning revolution marches on, self-supervised learning has garnered
increasing attention in recent years thanks to its remarkable representation learning ability …

3d cinemagraphy from a single image

X Li, Z Cao, H Sun, J Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
We present 3D Cinemagraphy, a new technique that marries 2D image animation with 3D
photography. Given a single still image as input, our goal is to generate a video that contains …

Neural video depth stabilizer

Y Wang, M Shi, J Li, Z Huang, Z Cao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Video depth estimation aims to infer temporally consistent depth. Some methods achieve
temporal consistency by finetuning a single-image depth model during test time using …

Mamo: Leveraging memory and attention for monocular video depth estimation

R Yasarla, H Cai, J Jeong, Y Shi… - Proceedings of the …, 2023 - openaccess.thecvf.com
We propose MAMo, a novel memory and attention framework for monocular video depth
estimation. MAMo can augment and improve any single-image depth estimation networks …

Constraining depth map geometry for multi-view stereo: A dual-depth approach with saddle-shaped depth cells

X Ye, W Zhao, T Liu, Z Huang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps
to achieve an accurate and complete 3D representation. Despite the excellent performance …

Match-stereo-videos: Bidirectional alignment for consistent dynamic stereo matching

J **g, Y Mao, K Mikolajczyk - European Conference on Computer Vision, 2024 - Springer
Dynamic stereo matching is the task of estimating consistent disparities from stereo videos
with dynamic objects. Recent learning-based methods prioritize optimal performance on a …

NVDS: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation

Y Wang, M Shi, J Li, C Hong, Z Huang… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Video depth estimation aims to infer temporally consistent depth. One approach is to
finetune a single-image model on each video with geometry constraints, which proves …

Futuredepth: Learning to predict the future improves video depth estimation

R Yasarla, MK Singh, H Cai, Y Shi, J Jeong… - … on Computer Vision, 2024 - Springer
In this paper, we propose a novel video depth estimation approach, FutureDepth, which
enables the model to implicitly leverage multi-frame and motion cues to improve depth …

Diffusion-augmented depth prediction with sparse annotations

J Li, Y Wang, Z Huang, J Zheng, K **an, Z Cao… - Proceedings of the 31st …, 2023 - dl.acm.org
Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity
of annotations makes the task challenging. Supervised models produce concave objects …