Related papers: Learning Pseudo Front Depth for 2D Forward-Looking…
Mobile robots operating indoors must be prepared to navigate challenging scenes that contain transparent surfaces. This paper proposes a novel method for the fusion of acoustic and visual sensing modalities through implicit neural…
Self-supervised surround-view depth estimation enables dense, low-cost 3D perception with a 360{\deg} field of view from multiple minimally overlapping images. Yet, most existing methods suffer from depth estimates that are inconsistent…
Digital elevation modeling of planetary surfaces is essential for studying past and ongoing geological processes. Wide-angle imagery acquired during spacecraft descent promises to offer a low-cost option for high-resolution terrain…
Self-supervised monocular depth estimation aims to infer depth information without relying on labeled data. However, the lack of labeled information poses a significant challenge to the model's representation, limiting its ability to…
Over the past few decades, we have witnessed a large family of algorithms that have been designed to provide different solutions to the problem of dimensionality reduction (DR). The DR is an essential tool to excavate the important…
Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth…
In this work, an approach based on a data-driven paradigm to denoise and mosaic acoustic camera images is proposed. Acoustic cameras, also known as 2D forward-looking sonar, could collect high-resolution acoustic images in dark and turbid…
Depth estimation is a cornerstone for autonomous driving, yet acquiring per-pixel depth ground truth for supervised learning is challenging. Self-Supervised Surround Depth Estimation (SSSDE) from consecutive images offers an economical…
In some scenarios, a single input image may not be enough to allow the object classification. In those cases, it is crucial to explore the complementary information extracted from images presenting the same object from multiple perspectives…
For monocular depth estimation, acquiring ground truths for real data is not easy, and thus domain adaptation methods are commonly adopted using the supervised synthetic data. However, this may still incur a large domain gap due to the lack…
Protoacoustic imaging showed great promise in providing real-time 3D dose verification of proton therapy. However, the limited acquisition angle in protoacoustic imaging induces severe artifacts, which significantly impairs its accuracy for…
Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from…
Multi-View Photometric Stereo (MVPS) is a popular method for fine-detailed 3D acquisition of an object from images. Despite its outstanding results on diverse material objects, a typical MVPS experimental setup requires a well-calibrated…
While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require…
Different from most state-of-the-art~(SOTA) algorithms that use static and uniform sampling methods with a lot of hypothesis planes to get fine depth sampling. In this paper, we propose a free-moving hypothesis plane method for dynamic and…
A recent strand of work in view synthesis uses deep learning to generate multiplane images (a camera-centric, layered 3D representation) given two or more input images at known viewpoints. We apply this representation to single-view view…
We propose an efficient multi-view stereo (MVS) network for infering depth value from multiple RGB images. Recent studies have shown that mapping the geometric relationship in real space to neural network is an essential topic of the MVS…
We propose an optimization technique for 3-D underwater object modeling from 2-D forward-scan sonar images at known poses. A key contribution, for objects imaged in the proximity of the sea surface, is to resolve the multipath artifacts due…
We present a real-time, non-learning depth estimation method that fuses Light Detection and Ranging (LiDAR) data with stereo camera input. Our approach comprises three key techniques: Semi-Global Matching (SGM) stereo with Discrete…
Volumetric depth map fusion based on truncated signed distance functions has become a standard method and is used in many 3D reconstruction pipelines. In this paper, we are generalizing this classic method in multiple ways: 1) Semantics:…