Related papers: Rethinking High-speed Image Reconstruction Framewo…

Single image scene relighting aims to generate a realistic new version of an input image so that it appears to be illuminated by a new target light condition. Although existing works have explored this problem from various perspectives,…

We present a fast and accurate method for dense depth reconstruction from sparsely sampled light fields obtained using a synchronized camera array. In our method, the source images are over-segmented into non-overlapping compact superpixels…

Scene reconstruction in the presence of high-speed motion and low illumination is important in many applications such as augmented and virtual reality, drone navigation, and autonomous robotics. Traditional motion estimation techniques fail…

Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to…

Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with respect to conventional cameras: high dynamic range (HDR),…

Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which…

Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains…

Capturing images under extremely low-light conditions poses significant challenges for the standard camera pipeline. Images become too dark and too noisy, which makes traditional enhancement techniques almost impossible to apply. Recently,…

Large-scale web-crawled datasets are fundamental for the success of pre-training vision-language models, such as CLIP. However, the inherent noise and potential irrelevance of web-crawled AltTexts pose challenges in achieving precise…

Image Quality Assessment (IQA) aims to evaluate the perceptual quality of images based on human subjective perception. Existing methods generally combine multiscale features to achieve high performance, but most rely on straightforward…

Photo search, the task of retrieving images based on textual queries, has witnessed significant advancements with the introduction of CLIP (Contrastive Language-Image Pretraining) model. CLIP leverages a vision-language pre training…

We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are typically constrained…

Convolutional neural networks (CNNs) are now the de facto solution for computer vision problems thanks to their impressive results and ease of learning. These networks are composed of layers of connected units called artificial neurons,…

Recent image tone adjustment (or enhancement) approaches have predominantly adopted supervised learning for learning human-centric perceptual assessment. However, these approaches are constrained by intrinsic challenges of supervised…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

In low-light conditions, a conventional camera imaging pipeline produces sub-optimal images that are usually dark and noisy due to a low photon count and low signal-to-noise ratio (SNR). We present a data-driven approach that learns the…

Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted…

Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the training data a significant factor in the efficacy of CLIP for…

Event cameras offer significant advantages over traditional frame-based sensors, including higher temporal resolution, lower latency and dynamic range. However, efficiently converting event streams into formats compatible with standard…

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single…