Related papers: MadEye: Boosting Live Video Analytics Accuracy wit…
Image-to-video adaptation seeks to efficiently adapt image models for use in the video domain. Instead of finetuning the entire image backbone, many image-to-video adaptation paradigms use lightweight adapters for temporal modeling on top…
Estimating eye-gaze from images alone is a challenging task, in large parts due to un-observable person-specific factors. Achieving high accuracy typically requires labeled data from test users which may not be attainable in real…
With the rapid proliferation of the Internet of Things, video analytics has become a cornerstone application in wireless multimedia sensor networks. To support such applications under bandwidth constraints, learning-based adaptive…
Most of current studies on human gaze and saliency modeling have used high-quality stimuli. In real world, however, captured images undergo various types of distortions during the whole acquisition, transmission, and displaying chain. Some…
Feed-forward foundation models for multi-view 3-dimensional (3D) reconstruction have been trained on large-scale datasets of perspective images; when tested on wide field-of-view images, e.g., from a fisheye camera, their performance…
Achieving physically accurate object manipulation in image editing is essential for its potential applications in interactive world models. However, existing visual generative models often fail at precise spatial manipulation, resulting in…
In the context of view-dependent point-cloud streaming in a scene, our rate allocation is "adaptive" in the sense that it priorities the point-cloud models depending on the camera view and the visibility of the objects and their distance as…
Optical motion capture (mocap) systems are widely used for ground-truth capture in AR/VR, SLAM and robotics datasets. These datasets require extrinsic calibration to align mocap coordinates to external camera frames -- a step that is…
Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central server to annotate data, which is then used to train…
It is well known that the accuracy of a calibration depends strongly on the choice of camera poses from which images of a calibration object are acquired. We present a system -- Calibration Wizard -- that interactively guides a user towards…
Meta-learning algorithms are widely used for few-shot learning. For example, image recognition systems that readily adapt to unseen classes after seeing only a few labeled examples. Despite their success, we show that modern meta-learning…
We propose PostCam, a framework for novel-view video generation that enables post-capture editing of camera trajectories in dynamic scenes. We find that existing video recapture methods suffer from suboptimal camera motion injection…
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…
A 360{\deg} perception of scene geometry is essential for automated driving, notably for parking and urban driving scenarios. Typically, it is achieved using surround-view fisheye cameras, focusing on the near-field area around the vehicle.…
The diffusion-based generative models have achieved remarkable success in text-based image generation. However, since it contains enormous randomness in generation progress, it is still challenging to apply such models for real-world visual…
Mobile devices increasingly rely on object detection (OD) through deep neural networks (DNNs) to perform critical tasks. Due to their high complexity, the execution of these DNNs requires excessive time and energy. Low-complexity object…
Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the…
Diffusion models offer unprecedented image generation power given just a text prompt. While emerging approaches for controlling diffusion models have enabled users to specify the desired spatial layouts of the generated content, they cannot…
Estimating absolute camera orientations is essential for attitude estimation tasks. An established approach is to first carry out visual odometry (VO) or visual SLAM (V-SLAM), and retrieve the camera orientations (3 DOF) from the camera…
Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving performance of efficient…