Related papers: Self-Supervised Surgical Instrument 3D Reconstruct…

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. In this paper, we…

We propose SIR, an efficient method to decompose differentiable shadows for inverse rendering on indoor scenes using multi-view data, addressing the challenges in accurately decomposing the materials and lighting conditions. Unlike previous…

Deep learning (DL) has emerged as a powerful tool for accelerated MRI reconstruction, but often necessitates a database of fully-sampled measurements for training. Recent self-supervised and unsupervised learning approaches enable training…

Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image with a multimodal query, i.e., a reference image, and its complementary modification text. As previous supervised or zero-shot learning paradigms…

We present a neural-field-based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions that are geometrically accurate and capture photo-realistic textures. This system adapts the…

Multispectral imaging (MSI) plays a critical role in material classification, environmental monitoring, and remote sensing. However, MSI sensors typically have wavelength-dependent resolution, which limits downstream analysis. MSI…

Single-pixel imaging (SPI) is an emerging technique which has attracts wide attention in various research fields. However, restricted by the low reconstruction quality and large amount of measurements, the practical application is still in…

Single image super-resolution (SISR) is an image processing task which obtains high-resolution (HR) image from a low-resolution (LR) image. Recently, due to the capability in feature extraction, a series of deep learning methods have…

Prior works for reconstructing hand-held objects from a single image train models on images paired with 3D shapes. Such data is challenging to gather in the real world at scale. Consequently, these approaches do not generalize well when…

Freehand 3D ultrasound (US) imaging using conventional 2D probes offers flexibility and accessibility for diverse clinical applications but faces challenges in accurate probe pose estimation. Traditional methods depend on costly tracking…

Segmentation of surgical instruments is an important problem in robot-assisted surgery: it is a crucial step towards full instrument pose estimation and is directly used for masking of augmented reality overlays during surgical procedures.…

3D ultrasound (US) is widely used for its rich diagnostic information. However, it is criticized for its limited field of view. 3D freehand US reconstruction is promising in addressing the problem by providing broad range and freeform scan.…

Super-resolution reconstruction (SRR) is a process aimed at enhancing spatial resolution of images, either from a single observation, based on the learned relation between low and high resolution, or from multiple images presenting the same…

Remote sensing image super-resolution (RSISR) is a crucial task in remote sensing image processing, aiming to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts. Despite the growing number of RSISR methods…

Monocular 3D reconstruction of articulated object categories is challenging due to the lack of training data and the inherent ill-posedness of the problem. In this work we use video self-supervision, forcing the consistency of consecutive…

This paper reports on a novel template-free monocular non-rigid surface reconstruction approach. Existing techniques using motion and deformation cues rely on multiple prior assumptions, are often computationally expensive and do not…

Medical instrument segmentation in 3D ultrasound is essential for image-guided intervention. However, to train a successful deep neural network for instrument segmentation, a large number of labeled images are required, which is expensive…

Recently, self-supervised learning (SSL) methods have been used in pre-training the segmentation models for 2D and 3D medical images. Most of these methods are based on reconstruction, contrastive learning and consistency regularization.…

We introduce a novel method to obtain high-quality 3D reconstructions from consumer RGB-D sensors. Our core idea is to simultaneously optimize for geometry encoded in a signed distance field (SDF), textures from automatically-selected…

Optimization-based approaches, such as score distillation sampling (SDS), show promise in zero-shot 3D generation but suffer from low efficiency, primarily due to the high number of function evaluations (NFEs) required for each sample and…