Related papers: Single-Frame based Deep View Synchronization for U…
This work presents an unsupervised learning based approach to the ubiquitous computer vision problem of image matching. We start from the insight that the problem of frame-interpolation implicitly solves for inter-frame correspondences.…
Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges…
Text-based 2D diffusion models have demonstrated impressive capabilities in image generation and editing. Meanwhile, the 2D diffusion models also exhibit substantial potentials for 3D editing tasks. However, how to achieve consistent edits…
In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or…
This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising…
Multi-view inverse rendering aims to recover geometry, materials, and illumination consistently across multiple viewpoints. When applied to multi-view images, existing single-view approaches often ignore cross-view relationships, leading to…
There have been significant advancements in dynamic novel view synthesis in recent years. However, current deep learning models often require (1) prior models (e.g., SMPL human models), (2) heavy pre-processing, or (3) per-scene…
Camera localization aims to estimate 6 DoF camera poses from RGB images. Traditional methods detect and match interest points between a query image and a pre-built 3D model. Recent learning-based approaches encode scene structures into a…
Recent 3D novel view synthesis (NVS) methods often require extensive 3D data for training, and also typically lack generalization beyond the training distribution. Moreover, they tend to be object centric and struggle with complex and…
Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic…
During the last decades, learning a low-dimensional space with discriminative information for dimension reduction (DR) has gained a surge of interest. However, it's not accessible for these DR methods to achieve satisfactory performance…
Novel view synthesis (NVS) from a single image is highly ill-posed due to large unobserved regions, especially for views that deviate significantly from the input. While existing methods focus on consistency between the source and generated…
Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…
In this work, we propose a novel unsupervised deep learning model to address multi-focus image fusion problem. First, we train an encoder-decoder network in unsupervised manner to acquire deep feature of input images. And then we utilize…
Advances in computer networks and rendering systems facilitate the creation of distributed collaborative environments in which the distribution of information at remote locations allows efficient communication. One of the challenges in…
Modern cameras with large apertures often suffer from a shallow depth of field, resulting in blurry images of objects outside the focal plane. This limitation is particularly problematic for fixed-focus cameras, such as those used in smart…
Multi-beam LiDAR sensors, as used on autonomous vehicles and mobile robots, acquire sequences of 3D range scans ("frames"). Each frame covers the scene sparsely, due to limited angular scanning resolution and occlusion. The sparsity…
We address the problem of recovering the 3D geometry of a human face from a set of facial images in multiple views. While recent studies have shown impressive progress in 3D Morphable Model (3DMM) based facial reconstruction, the settings…
Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains. Although the topic has attracted attention recently, current approaches all rely on the…
A realistic view of the vehicle's surroundings is generally offered by camera sensors, which is crucial for environmental perception. Affordable radar sensors, on the other hand, are becoming invaluable due to their robustness in variable…