On the opportunities and risks of foundation models
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
From big to small: Multi-scale local planar guidance for monocular depth estimation
Estimating accurate depth from a single image is challenging because it is an ill-posed
problem as infinitely many 3D scenes can be projected to the same 2D scene. However …
problem as infinitely many 3D scenes can be projected to the same 2D scene. However …
Soft rasterizer: A differentiable renderer for image-based 3d reasoning
Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical
process of image formation. By inverting such renderer, one can think of a learning …
process of image formation. By inverting such renderer, one can think of a learning …
Enforcing geometric constraints of virtual normal for depth prediction
Monocular depth prediction plays a crucial role in understanding 3D scene geometry.
Although recent methods have achieved impressive progress in evaluation metrics such as …
Although recent methods have achieved impressive progress in evaluation metrics such as …
Deep ordinal regression network for monocular depth estimation
Monocular depth estimation, which plays a crucial role in understanding 3D scene
geometry, is an ill-posed prob-lem. Recent methods have gained significant improvement by …
geometry, is an ill-posed prob-lem. Recent methods have gained significant improvement by …
Matterport3d: Learning from rgb-d data in indoor environments
Access to large, diverse RGB-D datasets is critical for training RGB-D scene understanding
algorithms. However, existing datasets still cover only a limited number of views or a …
algorithms. However, existing datasets still cover only a limited number of views or a …
Scaling and benchmarking self-supervised visual representation learning
Self-supervised learning aims to learn representations from the data itself without explicit
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …
Depth prediction without the sensors: Leveraging structure for unsupervised learning from monocular videos
Learning to predict scene depth from RGB inputs is a challenging task both for indoor and
outdoor robot navigation. In this work we address unsupervised learning of scene depth and …
outdoor robot navigation. In this work we address unsupervised learning of scene depth and …
Depth from videos in the wild: Unsupervised monocular depth learning from unknown cameras
We present a novel method for simultaneous learning of depth, egomotion, object motion,
and camera intrinsics from monocular videos, using only consistency across neighboring …
and camera intrinsics from monocular videos, using only consistency across neighboring …
Unsupervised monocular depth estimation with left-right consistency
Learning based methods have shown very promising results for the task of depth estimation
in single images. However, most existing approaches treat depth prediction as a supervised …
in single images. However, most existing approaches treat depth prediction as a supervised …