Related papers: CustomNet: Zero-shot Object Customization with Var…
Zero-shot learning, which aims to recognize new categories that are not included in the training set, has gained popularity owing to its potential ability in the real-word applications. Zero-shot learning models rely on learning an…
Recent remarkable advances in large-scale text-to-image diffusion models have inspired a significant breakthrough in text-to-3D generation, pursuing 3D content creation solely from a given text prompt. However, existing text-to-3D…
View synthesis is usually done by an autoencoder, in which the encoder maps a source view image into a latent content code, and the decoder transforms it into a target view image according to the condition. However, the source contents are…
Novel view synthesis has observed tremendous developments since the arrival of NeRFs. However, Nerf models overfit on a single scene, lacking generalization to out of distribution objects. Recently, diffusion models have exhibited…
Unsupervised video object learning seeks to decompose video scenes into structural object representations without any supervision from depth, optical flow, or segmentation. We present VONet, an innovative approach that is inspired by MONet.…
Customized image generation is essential for creating personalized content based on user prompts, allowing large-scale text-to-image diffusion models to more effectively meet individual needs. However, existing models often neglect the…
This paper introduces DCT-Net, a novel image translation architecture for few-shot portrait stylization. Given limited style exemplars ($\sim$100), the new architecture can produce high-quality style transfer results with advanced ability…
Text-to-image models give rise to workflows which often begin with an exploration step, where users sift through a large collection of generated images. The global nature of the text-to-image generation process prevents users from narrowing…
Recently, the use of synthetic datasets based on game engines has been shown to improve the performance of several tasks in computer vision. However, these datasets are typically only appropriate for the specific domains depicted in…
Recent diffusion-based text-to-image customization methods have achieved significant success in understanding concrete concepts to control generation processes, such as styles and shapes. However, few efforts dive into the realistic yet…
We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels…
Novel view synthesis is a challenging problem in computer vision and robotics. Different from the existing works, which need the reference images or 3D models of the scene to generate images under novel views, we propose a novel paradigm to…
Concept personalization methods enable large text-to-image models to learn specific subjects (e.g., objects/poses/3D models) and synthesize renditions in new contexts. Given that the image references are highly biased towards visual…
Text-to-image generation models represent the next step of evolution in image synthesis, offering a natural way to achieve flexible yet fine-grained control over the result. One emerging area of research is the fast adaptation of large…
The rapid advancement of diffusion models has increased the need for customized image generation. However, current customization methods face several limitations: 1) typically accept either image or text conditions alone; 2) customization…
Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing…
Recent studies on dense captioning and visual grounding in 3D have achieved impressive results. Despite developments in both areas, the limited amount of available 3D vision-language data causes overfitting issues for 3D visual grounding…
Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…
Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing. A number of recently proposed approaches utilize a fully supervised object recognition model within…
3D object detection is an essential task in autonomous driving and robotics. Though great progress has been made, challenges remain in estimating 3D pose for distant and occluded objects. In this paper, we present a novel framework named…