Related papers: Geo-NI: Geometry-aware Neural Interpolation for Li…

Recent 3D Gaussian Splatting (3DGS) representations have demonstrated remarkable performance in novel view synthesis; further, material-lighting disentanglement on 3DGS warrants relighting capabilities and its adaptability to broader…

Echo-planar imaging (EPI) remains the cornerstone of diffusion MRI, but it is prone to severe geometric distortions due to its rapid sampling scheme that renders the sequence highly sensitive to $B_{0}$ field inhomogeneities. While deep…

We propose SNI-SLAM, a semantic SLAM system utilizing neural implicit representation, that simultaneously performs accurate semantic mapping, high-quality surface reconstruction, and robust camera tracking. In this system, we introduce…

In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry, camera parameters, and a neural renderer that approximates…

Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\textit{i.e.}, StyleGAN2) as GAN Prior. However, these methods usually struggle to balance realness and fidelity when facing various degradation…

Reconstructing the shape and spatially varying surface appearances of a physical-world object as well as its surrounding illumination based on 2D images (e.g., photographs) of the object has been a long-standing problem in computer vision…

We propose LIRF (Local Implicit Ray Function), a generalizable neural rendering approach for novel view rendering. Current generalizable neural radiance fields (NeRF) methods sample a scene with a single ray per pixel and may therefore…

Neural Radiance Fields (NeRF) have transformed novel view synthesis by modeling scene-specific volumetric representations directly from images. While generalizable NeRF models can generate novel views across unknown scenes by learning…

Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task, particularly with real-world data. Current state-of-the-art methods develop Transformer-based implicit field learning, necessitating an…

We introduce a novel neural network-based BRDF model and a Bayesian framework for object inverse rendering, i.e., joint estimation of reflectance and natural illumination from a single image of an object of known geometry. The BRDF is…

We present a method that takes as input a set of images of a scene illuminated by unconstrained known lighting, and produces as output a 3D representation that can be rendered from novel viewpoints under arbitrary lighting conditions. Our…

Recovering the geometry and materials of objects from a single image is challenging due to its under-constrained nature. In this paper, we present Neural LightRig, a novel framework that boosts intrinsic estimation by leveraging auxiliary…

Computational imaging enables compact infrared systems, but deep-learning pipelines that combine image reconstruction and object detection often introduce substantial inference latency. Most existing acceleration strategies compress the…

Recently, learning-based ego-motion estimation approaches have drawn strong interest from studies mostly focusing on visual perception. These groundbreaking works focus on unsupervised learning for odometry estimation but mostly for visual…

How to balance training accuracy and adversarial robustness has become a challenge since the birth of deep learning. Here, we introduce a geometry-aware deep learning framework that leverages layer-wise local training to sculpt the internal…

Proximal gradient-based optimization is one of the most common strategies to solve inverse problem of images, and it is easy to implement. However, these techniques often generate heavy artifacts in image reconstruction. One of the most…

Generating realistic intermediate shapes between non-rigidly deformed shapes is a challenging task in computer vision, especially with unstructured data (e.g., point clouds) where temporal consistency across frames is lacking, and…

Neural Radiance Fields (NeRF) have been proposed for photorealistic novel view rendering. However, it requires many different views of one scene for training. Moreover, it has poor generalizations to new scenes and requires retraining or…

We propose ExtraNeRF, a novel method for extrapolating the range of views handled by a Neural Radiance Field (NeRF). Our main idea is to leverage NeRFs to model scene-specific, fine-grained details, while capitalizing on diffusion models to…

Existing methods for spectral reconstruction usually learn a discrete mapping from RGB images to a number of spectral bands. However, this modeling strategy ignores the continuous nature of spectral signature. In this paper, we propose…