相关论文: Explorable Tone Mapping Operators

Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and…

Image-text multimodal representation learning aligns data across modalities and enables important medical applications, e.g., image classification, visual grounding, and cross-modal retrieval. In this work, we establish a connection between…

Despite the significant progress in multimodal large language models (MLLMs), their high computational cost remains a barrier to real-world deployment. Inspired by the mixture of depths (MoDs) in natural language processing, we aim to…

Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced on-line iterative optimization, enabling nearly real-time stylization. When…

We present a learning-based technique for estimating high dynamic range (HDR), omnidirectional illumination from a single low dynamic range (LDR) portrait image captured under arbitrary indoor or outdoor lighting conditions. We train our…

Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although…

In the field of computer vision, multimodal image generation has become a research hotspot, especially the task of integrating text, image, and style. In this study, we propose a multimodal image generation method based on Generative…

We present a novel visual instruction tuning strategy to improve the zero-shot task generalization of multimodal large language models by building a firm text-only knowledge base. Existing work lacks sufficient experimentation on the…

The combination of range sensors with color cameras can be very useful for robot navigation, semantic perception, manipulation, and telepresence. Several methods of combining range- and color-data have been investigated and successfully…

High Dynamic Range (HDR) generation remains challenging for generative models, which are largely limited to low dynamic range outputs. Recent diffusionbased approaches approximate HDR by generating multiple exposure-conditioned samples,…

Feature matching is an important technique to identify a single object in different images. It helps machines to construct recognition of a specific object from multiple perspectives. For years, feature matching has been commonly used in…

Enhancement is an important step in post-processing digital images for personal use, in medical imaging, and for object recognition. Most existing manual techniques rely on region selection, similarity, and/or thresholding for editing,…

Dual learning has been successfully applied in many machine learning applications including machine translation, image-to-image transformation, etc. The high-level idea of dual learning is very intuitive: if we map an $x$ from one domain to…

In image-based camera localization systems, information about the environment is usually stored in some representation, which can be referred to as a map. Conventionally, most maps are built upon hand-crafted features. Recently, neural…

Multi-modal 3D medical image segmentation aims to accurately identify tumor regions across different modalities, facing challenges from variations in image intensity and tumor morphology. Traditional convolutional neural network (CNN)-based…

Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To…

We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. Using the HDR-NeRF, we are able to generate both novel HDR views and…

The Coherence Length Diagram and the related maps have been shown to represent a useful tool for image analysis. Setting threshold parameters is one of the most important issues when dealing with such applications, as they affect both the…

Multimodal interactive maps are a solution for presenting spatial information to visually impaired people. In this paper, we present an interactive multimodal map prototype that is based on a tactile paper map, a multi-touch screen and…

Recent advances in image-to-image translation have seen a rise in approaches generating diverse images through a single network. To indicate the target domain for a one-to-many mapping, the latent code is injected into the generator…