Related papers: Hyper-VolTran: Fast and Generalizable One-Shot Ima…

This paper tackles the problem of novel view synthesis from a single image. In particular, we target real-world scenes with rich geometric structure, a challenging task due to the large appearance variations of such scenes and the lack of…

Portrait stylization is a long-standing task enabling extensive applications. Although 2D-based methods have made great progress in recent years, real-world applications such as metaverse and games often demand 3D content. On the other…

In this work, we propose a novel method for generating 3D point clouds that leverage properties of hyper networks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a…

Recently, neural implicit surfaces learning by volume rendering has become popular for multi-view reconstruction. However, one key challenge remains: existing approaches lack explicit multi-view geometry constraints, hence usually fail to…

We present an approach that learns to synthesize high-quality, novel views of 3D objects or scenes, while providing fine-grained and precise control over the 6-DOF viewpoint. The approach is self-supervised and only requires 2D images and…

We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images,…

Neural implicit reconstruction via volume rendering has demonstrated its effectiveness in recovering dense 3D surfaces. However, it is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with…

Neural Radiance Fields (NeRF) have emerged as a powerful tool for creating highly detailed and photorealistic scenes. Existing methods for NeRF-based 3D style transfer need extensive per-scene optimization for single or multiple styles,…

We present a deep reinforcement learning method of progressive view inpainting for 3D point scene completion under volume guidance, achieving high-quality scene reconstruction from only a single depth image with severe occlusion. Our…

Volumetric neural rendering methods like NeRF generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time. On the other hand, deep multi-view stereo methods can quickly reconstruct…

Recovering the 3D geometric structure of a face from a single input image is a challenging active research area in computer vision. In this paper, we present a novel method for reconstructing 3D heads from a single or multiple image(s)…

Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matching. These architectures are specialized according to the…

Multi-view projection methods have demonstrated their ability to reach state-of-the-art performance on 3D shape recognition. Those methods learn different ways to aggregate information from multiple views. However, the camera view-points…

Recovering the 3D shape of an object from single or multiple images with deep neural networks has been attracting increasing attention in the past few years. Mainstream works (e.g. 3D-R2N2) use recurrent neural networks (RNNs) to…

This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view…

Hyperspectral image has become increasingly crucial due to its abundant spectral information. However, It has poor spatial resolution with the limitation of the current imaging mechanism. Nowadays, many convolutional neural networks have…

Rendering photorealistic and dynamically moving human heads is crucial for ensuring a pleasant and immersive experience in AR/VR and video conferencing applications. However, existing methods often struggle to model challenging facial…

Super-resolution reconstruction techniques entail the utilization of software algorithms to transform one or more sets of low-resolution images captured from the same scene into high-resolution images. In recent years, considerable…

We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a "foundation" model for monocular depth estimation and…

We present a novel method for performing flexible, 3D-aware image content manipulation while enabling high-quality novel view synthesis. While NeRF-based approaches are effective for novel view synthesis, such models memorize the radiance…