Related papers: DiFT: Differentiable Differential Feature Transfor…
Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i.e., when cameras are both internally and externally calibrated. Nevertheless, the challenge of simultaneous recovery of camera poses…
Reconstructing the geometry and appearance of objects from photographs taken in different environments is difficult as the illumination and therefore the object appearance vary across captured images. This is particularly challenging for…
Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic…
Three-dimensional (3D) object reconstruction based on differentiable rendering (DR) is an active research topic in computer vision. DR-based methods minimize the difference between the rendered and target images by optimizing both the shape…
Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision. Most approaches recover the depth at each pixel based on the focal setting which exhibits maximal sharpness. Yet, it is not obvious how to…
Stereo matching has become a key technique for 3D environment perception in intelligent vehicles. For a considerable time, convolutional neural networks (CNNs) have remained the mainstream choice for feature extraction in this domain.…
Depth estimation provides an alternative approach for perceiving 3D information in autonomous driving. Monocular depth estimation, whether with single-frame or multi-frame inputs, has achieved significant success by learning various types…
Recent neural view synthesis methods have achieved impressive quality and realism, surpassing classical pipelines which rely on multi-view reconstruction. State-of-the-Art methods, such as NeRF, are designed to learn a single scene with a…
Recently, high dynamic range (HDR) image reconstruction based on the multiple exposure stack from a given single exposure utilizes a deep learning framework to generate high-quality HDR images. These conventional networks focus on the…
Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed great success in cross-domain computer vision tasks, enhancing the generalization ability of data-driven deep learning architectures by bridging the domain…
Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…
We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes. It is a challenging problem to estimate dense pixel correspondences between images depicting different scenes or instances of the same…
Personalized image generation aims to faithfully preserve a reference subject's identity while adapting to diverse text prompts. Existing optimization-based methods ensure high fidelity but are computationally expensive, while…
This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that…
Fast and invariant feature extraction is crucial in certain computer vision applications where the computation time is constrained in both training and testing phases of the classifier. In this paper, we propose a nature-inspired…
We present a novel method for efficient acquisition of shape and spatially varying reflectance of 3D objects using polarization cues. Unlike previous works that have exploited polarization to estimate material or object appearance under…
Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…
We present a learning-based technique for estimating high dynamic range (HDR), omnidirectional illumination from a single low dynamic range (LDR) portrait image captured under arbitrary indoor or outdoor lighting conditions. We train our…
This paper presents Camera-LiDAR Fusion Transformer (CLFT) models for traffic object segmentation, which leverage the fusion of camera and LiDAR data using vision transformers. Building on the methodology of visual transformers that exploit…
Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training…