Depthcrafter: Generating consistent long depth sequences for open-world videos
Despite significant advancements in monocular depth estimation for static images,
estimating video depth in the open world remains challenging, since open-world videos are …
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
As the deep learning revolution marches on, self-supervised learning has garnered
increasing attention in recent years thanks to its remarkable representation learning ability …
increasing attention in recent years thanks to its remarkable representation learning ability …
3d cinemagraphy from a single image
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 …
photography. Given a single still image as input, our goal is to generate a video that contains …
Neural video depth stabilizer
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 …
temporal consistency by finetuning a single-image depth model during test time using …
Mamo: Leveraging memory and attention for monocular video depth estimation
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 …
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
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 …
to achieve an accurate and complete 3D representation. Despite the excellent performance …
Match-stereo-videos: Bidirectional alignment for consistent dynamic stereo matching
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 …
with dynamic objects. Recent learning-based methods prioritize optimal performance on a …
NVDS: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation
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 …
finetune a single-image model on each video with geometry constraints, which proves …
Futuredepth: Learning to predict the future improves video depth estimation
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 …
enables the model to implicitly leverage multi-frame and motion cues to improve depth …
Diffusion-augmented depth prediction with sparse annotations
Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity
of annotations makes the task challenging. Supervised models produce concave objects …
of annotations makes the task challenging. Supervised models produce concave objects …