Category-level object pose estimation, aiming to predict the 6D pose and 3D size of objects from known categories, typically struggles with large intra-class shape variation. Existing works utilizing mean shapes often fall short of capturing this variation. To address this issue, we present SecondPose, a novel approach integrating object-specific geometric features with semantic category priors from DINOv2. Leveraging the advantage of DINOv2 in providing SE(3)-consistent semantic features, we hierarchically extract two types of SE(3)-invariant geometric features to further encapsulate local-to-global object-specific information. These geometric features are then point-aligned with DINOv2 features to establish a consistent object representation under SE(3) transformations, facilitating the mapping from camera space to the pre-defined canonical space, thus further enhancing pose estimation. Extensive experiments on NOCS-REAL275 demonstrate that SecondPose achieves a 12.4% leap forward over the state-of-the-art. Moreover, on a more complex dataset HouseCat6D which provides photometrically challenging objects, SecondPose still surpasses other competitors by a large margin. The code will be released soon.
Robotic ophthalmic surgery is an emerging technology to facilitate high-precision interventions such as retina penetration in subretinal injection and removal of floating tissues in retinal detachment depending on the input imaging modalities such as microscopy and intraoperative OCT (iOCT). Although iOCT is explored to locate the needle tip within its range-limited ROI, it is still difficult to coordinate iOCT's motion with the needle, especially at the initial target-approaching stage. Meanwhile, due to 2D perspective projection and thus the loss of depth information, current image-based methods cannot effectively estimate the needle tip's trajectory towards both retinal and floating targets. To address this limitation, we propose to use the shadow positions of the target and the instrument tip to estimate their relative depth position and accordingly optimize the instrument tip's insertion trajectory until the tip approaches targets within iOCT's scanning area. Our method succeeds target approaching on a retina model, and achieves an average depth error of 0.0127 mm and 0.3473 mm for floating and retinal targets respectively in the surgical simulator without damaging the retina.
Creating high-quality view synthesis is essential for immersive applications but continues to be problematic, particularly in indoor environments and for real-time deployment. Current techniques frequently require extensive computational time for both training and rendering, and often produce less-than-ideal 3D representations due to inadequate geometric structuring. To overcome this, we introduce VoxNeRF, a novel approach that leverages volumetric representations to enhance the quality and efficiency of indoor view synthesis. Firstly, VoxNeRF constructs a structured scene geometry and converts it into a voxel-based representation. We employ multi-resolution hash grids to adaptively capture spatial features, effectively managing occlusions and the intricate geometry of indoor scenes. Secondly, we propose a unique voxel-guided efficient sampling technique. This innovation selectively focuses computational resources on the most relevant portions of ray segments, substantially reducing optimization time. We validate our approach against three public indoor datasets and demonstrate that VoxNeRF outperforms state-of-the-art methods. Remarkably, it achieves these gains while reducing both training and rendering times, surpassing even Instant-NGP in speed and bringing the technology closer to real-time.
Ultrasound (US) imaging is widely used in diagnosing and staging abdominal diseases due to its lack of non-ionizing radiation and prevalent availability. However, significant inter-operator variability and inconsistent image acquisition hinder the widespread adoption of extensive screening programs. Robotic ultrasound systems have emerged as a promising solution, offering standardized acquisition protocols and the possibility of automated acquisition. Additionally, these systems enable access to 3D data via robotic tracking, enhancing volumetric reconstruction for improved ultrasound interpretation and precise disease diagnosis. However, the interpretability of 3D US reconstruction of abdominal images can be affected by the patient's breathing motion. This study introduces a method to compensate for breathing motion in 3D US compounding by leveraging implicit neural representations. Our approach employs a robotic ultrasound system for automated screenings. To demonstrate the method's effectiveness, we evaluate our proposed method for the diagnosis and monitoring of abdominal aorta aneurysms as a representative use case. Our experiments demonstrate that our proposed pipeline facilitates robust automated robotic acquisition, mitigating artifacts from breathing motion, and yields smoother 3D reconstructions for enhanced screening and medical diagnosis.
Scene graphs have emerged as accurate descriptive priors for image generation and manipulation tasks, however, their complexity and diversity of the shapes and relations of objects in data make it challenging to incorporate them into the models and generate high-quality results. To address these challenges, we propose PRISM, a novel progressive multi-head image manipulation approach to improve the accuracy and quality of the manipulated regions in the scene. Our image manipulation framework is trained using an end-to-end denoising masked reconstruction proxy task, where the masked regions are progressively unmasked from the outer regions to the inner part. We take advantage of the outer part of the masked area as they have a direct correlation with the context of the scene. Moreover, our multi-head architecture simultaneously generates detailed object-specific regions in addition to the entire image to produce higher-quality images. Our model outperforms the state-of-the-art methods in the semantic image manipulation task on the CLEVR and Visual Genome datasets. Our results demonstrate the potential of our approach for enhancing the quality and precision of scene graph-based image manipulation.
Surgical videos captured from microscopic or endoscopic imaging devices are rich but complex sources of information, depicting different tools and anatomical structures utilized during an extended amount of time. Despite containing crucial workflow information and being commonly recorded in many procedures, usage of surgical videos for automated surgical workflow understanding is still limited. In this work, we exploit scene graphs as a more holistic, semantically meaningful and human-readable way to represent surgical videos while encoding all anatomical structures, tools, and their interactions. To properly evaluate the impact of our solutions, we create a scene graph dataset from semantic segmentations from the CaDIS and CATARACTS datasets. We demonstrate that scene graphs can be leveraged through the use of graph convolutional networks (GCNs) to tackle surgical downstream tasks such as surgical workflow recognition with competitive performance. Moreover, we demonstrate the benefits of surgical scene graphs regarding the explainability and robustness of model decisions, which are crucial in the clinical setting.
To date, endovascular surgeries are performed using the golden standard of Fluoroscopy, which uses ionising radiation to visualise catheters and vasculature. Prolonged Fluoroscopic exposure is harmful for the patient and the clinician, and may lead to severe post-operative sequlae such as the development of cancer. Meanwhile, the use of interventional Ultrasound has gained popularity, due to its well-known benefits of small spatial footprint, fast data acquisition, and higher tissue contrast images. However, ultrasound images are hard to interpret, and it is difficult to localise vessels, catheters, and guidewires within them. This work proposes a solution using an adaptation of a state-of-the-art machine learning transformer architecture to detect and segment catheters in axial interventional Ultrasound image sequences. The network architecture was inspired by the Attention in Attention mechanism, temporal tracking networks, and introduced a novel 3D segmentation head that performs 3D deconvolution across time. In order to facilitate training of such deep learning networks, we introduce a new data synthesis pipeline that used physics-based catheter insertion simulations, along with a convolutional ray-casting ultrasound simulator to produce synthetic ultrasound images of endovascular interventions. The proposed method is validated on a hold-out validation dataset, thus demonstrated robustness to ultrasound noise and a wide range of scanning angles. It was also tested on data collected from silicon-based aorta phantoms, thus demonstrated its potential for translation from sim-to-real. This work represents a significant step towards safer and more efficient endovascular surgery using interventional ultrasound.
Object rearrangement is pivotal in robotic-environment interactions, representing a significant capability in embodied AI. In this paper, we present SG-Bot, a novel rearrangement framework that utilizes a coarse-to-fine scheme with a scene graph as the scene representation. Unlike previous methods that rely on either known goal priors or zero-shot large models, SG-Bot exemplifies lightweight, real-time, and user-controllable characteristics, seamlessly blending the consideration of commonsense knowledge with automatic generation capabilities. SG-Bot employs a three-fold procedure--observation, imagination, and execution--to adeptly address the task. Initially, objects are discerned and extracted from a cluttered scene during the observation. These objects are first coarsely organized and depicted within a scene graph, guided by either commonsense or user-defined criteria. Then, this scene graph subsequently informs a generative model, which forms a fine-grained goal scene considering the shape information from the initial scene and object semantics. Finally, for execution, the initial and envisioned goal scenes are matched to formulate robotic action policies. Experimental results demonstrate that SG-Bot outperforms competitors by a large margin.
Unlike in natural images, in endoscopy there is no clear notion of an up-right camera orientation. Endoscopic videos therefore often contain large rotational motions, which require keypoint detection and description algorithms to be robust to these conditions. While most classical methods achieve rotation-equivariant detection and invariant description by design, many learning-based approaches learn to be robust only up to a certain degree. At the same time learning-based methods under moderate rotations often outperform classical approaches. In order to address this shortcoming, in this paper we propose RIDE, a learning-based method for rotation-equivariant detection and invariant description. Following recent advancements in group-equivariant learning, RIDE models rotation-equivariance implicitly within its architecture. Trained in a self-supervised manner on a large curation of endoscopic images, RIDE requires no manual labeling of training data. We test RIDE in the context of surgical tissue tracking on the SuPeR dataset as well as in the context of relative pose estimation on a repurposed version of the SCARED dataset. In addition we perform explicit studies showing its robustness to large rotations. Our comparison against recent learning-based and classical approaches shows that RIDE sets a new state-of-the-art performance on matching and relative pose estimation tasks and scores competitively on surgical tissue tracking.
Dynamic reconstruction with neural radiance fields (NeRF) requires accurate camera poses. These are often hard to retrieve with existing structure-from-motion (SfM) pipelines as both camera and scene content can change. We propose DynaMoN that leverages simultaneous localization and mapping (SLAM) jointly with motion masking to handle dynamic scene content. Our robust SLAM-based tracking module significantly accelerates the training process of the dynamic NeRF while improving the quality of synthesized views at the same time. Extensive experimental validation on TUM RGB-D, BONN RGB-D Dynamic and the DyCheck's iPhone dataset, three real-world datasets, shows the advantages of DynaMoN both for camera pose estimation and novel view synthesis.