Related papers: SfM-TTR: Using Structure from Motion for Test-Time…
Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and…
Image retrieval is a critical step for reducing the quadratic cost of image matching in unconstrained Structure-from-Motion (SfM). Unlike generic image retrieval, however, the relevant goal of SfM is to identify geometrically matchable…
Recently, deep learning based video super-resolution (SR) methods have achieved promising performance. To simultaneously exploit the spatial and temporal information of videos, employing 3-dimensional (3D) convolutions is a natural…
Recent multimodal large language models (MLLM) such as GPT-4o and GPT-4v have shown great potential in autonomous driving. In this paper, we propose a cross-domain few-shot in-context learning method based on the MLLM for enhancing traffic…
Infrared thermography has been widely used in several domains to capture and measure temperature distributions across surfaces and objects. This methodology can be further expanded to 3D applications if the spatial distribution of the…
Despite that convolutional neural networks (CNN) have recently demonstrated high-quality reconstruction for single-image super-resolution (SR), recovering natural and realistic texture remains a challenging problem. In this paper, we show…
The fine timing measurement (FTM) protocol is designed to determine precise ranging between Wi-Fi devices using round-trip time (RTT) measurements. However, the multipath propagation of radio waves generates inaccurate timing information,…
Low-light image super-resolution (LLISR) is essential for restoring fine visual details and perceptual quality under insufficient illumination conditions with ubiquitous low-resolution devices. Although pioneer methods achieve high…
Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack…
Self-supervised learning aims to learn image feature representations without the usage of manually annotated labels. It is often used as a precursor step to obtain useful initial network weights which contribute to faster convergence and…
Images captured under extremely low light conditions are noise-limited, which can cause existing robotic vision algorithms to fail. In this paper we develop an image processing technique for aiding 3D reconstruction from images acquired in…
Current non-rigid structure from motion (NRSfM) algorithms are mainly limited with respect to: (i) the number of images, and (ii) the type of shape variability they can handle. This has hampered the practical utility of NRSfM for many…
Despite much recent progress in video-based person re-identification (re-ID), the current state-of-the-art still suffers from common real-world challenges such as appearance similarity among various people, occlusions, and frame…
There has been tremendous research progress in estimating the depth of a scene from a monocular camera image. Existing methods for single-image depth prediction are exclusively based on deep neural networks, and their training can be…
Single-view depth estimation (SVDE) plays a crucial role in scene understanding for AR applications, 3D modeling, and robotics, providing the geometry of a scene based on a single image. Recent works have shown that a successful solution…
Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…
Using only image-sentence pairs, weakly-supervised visual-textual grounding aims to learn region-phrase correspondences of the respective entity mentions. Compared to the supervised approach, learning is more difficult since bounding boxes…
We present SLAIM - Simultaneous Localization and Implicit Mapping. We propose a novel coarse-to-fine tracking model tailored for Neural Radiance Field SLAM (NeRF-SLAM) to achieve state-of-the-art tracking performance. Notably, existing…
Multimodal large language models (MLLMs) have advanced from image-level reasoning to pixel-level grounding, but extending these capabilities to videos remains challenging as models must achieve spatial precision and temporally consistent…
Robust object tracking requires knowledge of tracked objects' appearance, motion and their evolution over time. Although motion provides distinctive and complementary information especially for fast moving objects, most of the recent…