Related papers: CLIP-based Neural Neighbor Style Transfer for 3D A…

Convolutional Neural Networks (CNNs) have become the state-of-the-art method to learn from image data. However, recent research shows that they may include a texture and colour bias in their representation, contrary to the intuition that…

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…

Conventional 3D style transfer methods rely on a fixed reference image to apply artistic patterns to 3D scenes. However, in practical applications such as virtual or augmented reality, users often prefer more flexible inputs, including…

In this work, we have investigated various style transfer approaches and (i) examined how the stylized reconstruction changes with the change of loss function and (ii) provided a computationally efficient solution for the same. We have used…

Controllable 3D style transfer seeks to restyle a 3D asset so that its textures match a reference image while preserving the integrity and multi-view consistency. The prevalent methods either rely on direct reference style token injection…

When creating 3D content, highly specialized skills are generally needed to design and generate models of objects and other assets by hand. We address this problem through high-quality 3D asset retrieval from multi-modal inputs, including…

Artistic style transfer aims to use a style image and a content image to synthesize a target image that retains the same artistic expression as the style image while preserving the basic content of the content image. Many recently proposed…

3D stylization, the application of specific styles to three-dimensional objects, offers substantial commercial potential by enabling the creation of uniquely styled 3D objects tailored to diverse scenes. Recent advancements in artificial…

This paper investigates multi-scale feature approximation and transferable features for object detection from point clouds. Multi-scale features are critical for object detection from point clouds. However, multi-scale feature learning…

We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual…

Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is…

Recently, the progress of learning-by-synthesis has proposed a training model for synthetic images, which can effectively reduce the cost of human and material resources. However, due to the different distribution of synthetic images…

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…

Gaussian Splatting (GS) has recently emerged as an efficient representation for rendering 3D scenes from 2D images and has been extended to images, videos, and dynamic 4D content. However, applying style transfer to GS-based…

We present an approach to example-based stylization of images that uses a single pair of a source image and its stylized counterpart. We demonstrate how to train an image translation network that can perform real-time semantically…

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…

This paper presents an automatic image synthesis method to transfer the style of an example image to a content image. When standard neural style transfer approaches are used, the textures and colours in different semantic regions of the…

Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss. The triplet loss used in video re-ID is usually based on so-called clip features, each aggregated from…

In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings. Given an input, potentially incomplete, 3D scene and a query location, our method predicts a…

We present ShapeClipper, a novel method that reconstructs 3D object shapes from real-world single-view RGB images. Instead of relying on laborious 3D, multi-view or camera pose annotation, ShapeClipper learns shape reconstruction from a set…