Related papers: Rethinking High-speed Image Reconstruction Framewo…
Low-light images suffer from severe noise and low illumination. Current deep learning models that are trained with real-world images have excellent noise reduction, but a ratio parameter must be chosen manually to complete the enhancement…
Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize…
The Contrastive Language-Image Pre-training (CLIP) Model is a recently proposed large-scale pre-train model which attracts increasing attention in the computer vision community. Benefiting from its gigantic image-text training set, the CLIP…
We introduce the concept of a subjective camera to reconstruct meaningful moments that physical cameras fail to capture. We propose Subjective Camera 1.0, a framework for reconstructing real-world scenes from readily accessible subjective…
Although CLIP-like Visual Language Models provide a functional joint feature space for image and text, due to the limitation of the CILP-like model's image input size (e.g., 224), subtle details are lost in the feature representation if we…
Creating datasets for Neuromorphic Vision is a challenging task. A lack of available recordings from Neuromorphic Vision sensors means that data must typically be recorded specifically for dataset creation rather than collecting and…
High throughput video acquisition is a challenging problem and has been drawing increasing attention. Existing high throughput imaging systems splice hundreds of sub-images/videos into high throughput videos, suffering from extremely high…
CLIP has shown promising performance across many short-text tasks in a zero-shot manner. However, limited by the input length of the text encoder, CLIP struggles on under-stream tasks with long-text inputs ($>77$ tokens). To remedy this…
Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which…
Under-display cameras have been proposed in recent years as a way to reduce the form factor of mobile devices while maximizing the screen area. Unfortunately, placing the camera behind the screen results in significant image distortions,…
The process through which humans perceive and learn visual representations in dynamic environments is highly complex. From a structural perspective, the human eye decouples the functions of cone and rod cells: cones are primarily…
With the rise of Extended Reality (XR) technology, there is a growing need for real-time light field reconstruction from sparse view inputs. Existing methods can be classified into offline techniques, which can generate high-quality novel…
Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained…
We present a spike-based unsupervised regenerative learning scheme to train Spiking Deep Networks (SpikeCNN) for object recognition problems using biologically realistic leaky integrate-and-fire neurons. The training methodology is based on…
Lensless imaging has emerged as a potential solution towards realizing ultra-miniature cameras by eschewing the bulky lens in a traditional camera. Without a focusing lens, the lensless cameras rely on computational algorithms to recover…
Video Snapshot Compressive Imaging (SCI) aims to use a low-speed 2D camera to capture high-speed scene as snapshot compressed measurements, followed by a reconstruction algorithm to reconstruct the high-speed video frames. State-of-the-art…
Recent significant advances in text-to-image models unlock the possibility of training vision systems using synthetic images, potentially overcoming the difficulty of collecting curated data at scale. It is unclear, however, how these…
Spikes are the currency in central nervous systems for information transmission and processing. They are also believed to play an essential role in low-power consumption of the biological systems, whose efficiency attracts increasing…
Neuromorphic imaging is an emerging technique that imitates the human retina to sense variations in dynamic scenes. It responds to pixel-level brightness changes by asynchronous streaming events and boasts microsecond temporal precision…
Traditional image signal processing (ISP) pipeline consists of a set of individual image processing components onboard a camera to reconstruct a high-quality sRGB image from the sensor raw data. Due to the hand-crafted nature of the ISP…