Related papers: STATIC : Surface Temporal Affine for TIme Consiste…
Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with…
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across…
Self-supervised monocular depth estimation is an attractive solution that does not require hard-to-source depth labels for training. Convolutional neural networks (CNNs) have recently achieved great success in this task. However, their…
Detecting what has changed in an environment is essential for long-term autonomy, yet most change detection settings assume fixed viewpoints, mild misalignment, or only a few changed objects. We introduce Video-based Scene Change Detection…
Learning to predict scene depth and camera motion from RGB inputs only is a challenging task. Most existing learning based methods deal with this task in a supervised manner which require ground-truth data that is expensive to acquire. More…
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we…
Self-supervised monocular scene flow estimation, aiming to understand both 3D structures and 3D motions from two temporally consecutive monocular images, has received increasing attention for its simple and economical sensor setup. However,…
Applying image processing algorithms independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our…
Conventional video matting outputs one alpha matte for all instances appearing in a video frame so that individual instances are not distinguished. While video instance segmentation provides time-consistent instance masks, results are…
Temporal modeling and spatio-temporal collaboration are pivotal techniques for video-based human pose estimation. Most state-of-the-art methods adopt optical flow or temporal difference, learning local visual content correspondence across…
Monocular depth estimation has recently progressed beyond ordinal depth to provide metric depth predictions. However, its reliability in underwater environments remains limited due to light attenuation and scattering, color distortion,…
Managing the dynamic regions in the photometric loss formulation has been a main issue for handling the self-supervised depth estimation problem. Most previous methods have alleviated this issue by removing the dynamic regions in the…
Accurate depth estimation is fundamental to 3D perception in autonomous driving, supporting tasks such as detection, tracking, and motion planning. However, monocular camera-based 3D detection suffers from depth ambiguity and reduced…
We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main…
Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usually violated in the…
Monocular depth estimation plays a crucial role in 3D recognition and understanding. One key limitation of existing approaches lies in their lack of structural information exploitation, which leads to inaccurate spatial layout,…
In this paper, we propose a novel learning scheme for self-supervised video representation learning. Motivated by how humans understand videos, we propose to first learn general visual concepts then attend to discriminative local areas for…
Reconstructing spatially and temporally coherent videos from time-varying measurements is a fundamental challenge in many scientific domains. A major difficulty arises from the sparsity of measurements, which hinders accurate recovery of…
Previous methods for dynamic facial expression in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. To solve this problem, we propose the spatio-temporal…
Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task that often relies on the so-called scene rigidity assumption. When observing a dynamic environment, this…