相关论文: GANESH: Generalizable NeRF for Lensless Imaging

Novel view synthesis using neural radiance fields (NeRF) is the state-of-the-art technique for generating high-quality images from novel viewpoints. Existing methods require a priori knowledge about extrinsic and intrinsic camera…

Panoramic observation using fisheye cameras is significant in virtual reality (VR) and robot perception. However, panoramic images synthesized by traditional methods lack depth information and can only provide three degrees-of-freedom…

Recovering a textured 3D mesh from a monocular image is highly challenging, particularly for in-the-wild objects that lack 3D ground truths. In this work, we present MeshInversion, a novel framework to improve the reconstruction by…

The speckle field yielded by disordered media is extensively employed for spectral measurements. Existing speckle reconstructive spectrometers (RSs) implemented by neural networks primarily rely on supervised learning, which necessitates…

Many applications and algorithms in the field of gravitational lensing make use of meshes with a finite number of nodes to analyze and manipulate data. Specific examples in lensing are astronomical CCD images in general, the reconstruction…

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

Novel View Synthesis (NVS) from unconstrained photo collections is challenging in computer graphics. Recently, 3D Gaussian Splatting (3DGS) has shown promise for photorealistic and real-time NVS of static scenes. Building on 3DGS, we…

3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes. However, recovering a high-quality NeRF typically requires tens to hundreds of input images, resulting in a…

Mesh reconstruction from Neural Radiance Fields (NeRF) is widely used in 3D reconstruction and has been applied across numerous domains. However, existing methods typically rely solely on the given training set images, which restricts…

Generation of photo-realistic images, semantic editing and representation learning are a few of many potential applications of high resolution generative models. Recent progress in GANs have established them as an excellent choice for such…

This paper proposes a novel framework for large-scale scene reconstruction based on 3D Gaussian splatting (3DGS) and aims to address the scalability and accuracy challenges faced by existing methods. For tackling the scalability issue, we…

Lensless imaging seeks to replace/remove the lens in a conventional imaging system. The earliest cameras were in fact lensless, relying on long exposure times to form images on the other end of a small aperture in a darkened room/container…

Generalizable Neural Radiance Fields (GeNeRFs) enable high-quality scene reconstruction from sparse views and can generalize to unseen scenes. However, in real-world settings, transient distractors break cross-view structural consistency,…

Polarization imaging captures the polarization state of light, revealing information invisible to the human eye yet valuable in domains such as biomedical diagnostics, autonomous driving, and remote sensing. However, conventional…

Recently, Neural Radiance Fields (NeRF) have emerged as a potent method for synthesizing novel views from a dense set of images. Despite its impressive performance, NeRF is plagued by its necessity for numerous calibrated views and its…

Novel view synthesis (NVS) aims to generate images at arbitrary viewpoints using multi-view images, and recent insights from neural radiance fields (NeRF) have contributed to remarkable improvements. Recently, studies on generalizable NeRF…

Reconstruction and intrinsic decomposition of scenes from captured imagery would enable many applications such as relighting and virtual object insertion. Recent NeRF based methods achieve impressive fidelity of 3D reconstruction, but bake…

Recent methods for 3D reconstruction and rendering increasingly benefit from end-to-end optimization of the entire image formation process. However, this approach is currently limited: effects of the optical hardware stack and in particular…

We address a challenging lifelong few-shot image generation task for the first time. In this situation, a generative model learns a sequence of tasks using only a few samples per task. Consequently, the learned model encounters both…

Deep learning-based multi-view facial capture methods have shown impressive accuracy while being several orders of magnitude faster than a traditional mesh registration pipeline. However, the existing systems (e.g. TEMPEH) are strictly…