We propose a novel geometric and photometric 3D mapping pipeline for accurate and real-time scene reconstruction from monocular images. To achieve this, we leverage recent advances in dense monocular SLAM and real-time hierarchical volumetric neural radiance fields. Our insight is that dense monocular SLAM provides the right information to fit a neural radiance field of the scene in real-time, by providing accurate pose estimates and depth-maps with associated uncertainty. With our proposed uncertainty-based depth loss, we achieve not only good photometric accuracy, but also great geometric accuracy. In fact, our proposed pipeline achieves better geometric and photometric accuracy than competing approaches (up to 179% better PSNR and 86% better L1 depth), while working in real-time and using only monocular images.
相關內容
Simultaneous localization and mapping (SLAM) is one of the key components of a control system that aims to ensure autonomous navigation of a mobile robot in unknown environments. In a variety of practical cases a robot might need to travel long distances in order to accomplish its mission. This requires long-term work of SLAM methods and building large maps. Consequently the computational burden (including high memory consumption for map storage) becomes a bottleneck. Indeed, state-of-the-art SLAM algorithms include specific techniques and optimizations to tackle this challenge, still their performance in long-term scenarios needs proper assessment. To this end, we perform an empirical evaluation of two widespread state-of-the-art RGB-D SLAM methods, suitable for long-term navigation, i.e. RTAB-Map and Voxgraph. We evaluate them in a large simulated indoor environment, consisting of corridors and halls, while varying the odometer noise for a more realistic setup. We provide both qualitative and quantitative analysis of both methods uncovering their strengths and weaknesses. We find that both methods build a high-quality map with low odometry noise but tend to fail with high odometry noise. Voxgraph has lower relative trajectory estimation error and memory consumption than RTAB-Map, while its absolute error is higher.
Reflections on glossy objects contain valuable and hidden information about the surrounding environment. By converting these objects into cameras, we can unlock exciting applications, including imaging beyond the camera's field-of-view and from seemingly impossible vantage points, e.g. from reflections on the human eye. However, this task is challenging because reflections depend jointly on object geometry, material properties, the 3D environment, and the observer viewing direction. Our approach converts glossy objects with unknown geometry into radiance-field cameras to image the world from the object's perspective. Our key insight is to convert the object surface into a virtual sensor that captures cast reflections as a 2D projection of the 5D environment radiance field visible to the object. We show that recovering the environment radiance fields enables depth and radiance estimation from the object to its surroundings in addition to beyond field-of-view novel-view synthesis, i.e. rendering of novel views that are only directly-visible to the glossy object present in the scene, but not the observer. Moreover, using the radiance field we can image around occluders caused by close-by objects in the scene. Our method is trained end-to-end on multi-view images of the object and jointly estimates object geometry, diffuse radiance, and the 5D environment radiance field.
In this paper, we present a novel and effective framework, named 4K-NeRF, to pursue high fidelity view synthesis on the challenging scenarios of ultra high resolutions, building on the methodology of neural radiance fields (NeRF). The rendering procedure of NeRF-based methods typically relies on a pixel wise manner in which rays (or pixels) are treated independently on both training and inference phases, limiting its representational ability on describing subtle details especially when lifting to a extremely high resolution. We address the issue by better exploring ray correlation for enhancing high-frequency details benefiting from the use of geometry-aware local context. Particularly, we use the view-consistent encoder to model geometric information effectively in a lower resolution space and recover fine details through the view-consistent decoder, conditioned on ray features and depths estimated by the encoder. Joint training with patch-based sampling further facilitates our method incorporating the supervision from perception oriented regularization beyond pixel wise loss. Quantitative and qualitative comparisons with modern NeRF methods demonstrate that our method can significantly boost rendering quality for retaining high-frequency details, achieving the state-of-the-art visual quality on 4K ultra-high-resolution scenario. Code Available at \url{//github.com/frozoul/4K-NeRF}
Medical images play an important role in clinical applications. Multimodal medical images could provide rich information about patients for physicians to diagnose. The image fusion technique is able to synthesize complementary information from multimodal images into a single image. This technique will prevent radiologists switch back and forth between different images and save lots of time in the diagnostic process. In this paper, we introduce a novel Dilated Residual Attention Network for the medical image fusion task. Our network is capable to extract multi-scale deep semantic features. Furthermore, we propose a novel fixed fusion strategy termed Softmax-based weighted strategy based on the Softmax weights and matrix nuclear norm. Extensive experiments show our proposed network and fusion strategy exceed the state-of-the-art performance compared with reference image fusion methods on four commonly used fusion metrics.
Underwater navigation presents several challenges, including unstructured unknown environments, lack of reliable localization systems (e.g., GPS), and poor visibility. Furthermore, good-quality obstacle detection sensors for underwater robots are scant and costly; and many sensors like RGB-D cameras and LiDAR only work in-air. To enable reliable mapless underwater navigation despite these challenges, we propose a low-cost end-to-end navigation system, based on a monocular camera and a fixed single-beam echo-sounder, that efficiently navigates an underwater robot to waypoints while avoiding nearby obstacles. Our proposed method is based on Proximal Policy Optimization (PPO), which takes as input current relative goal information, estimated depth images, echo-sounder readings, and previous executed actions, and outputs 3D robot actions in a normalized scale. End-to-end training was done in simulation, where we adopted domain randomization (varying underwater conditions and visibility) to learn a robust policy against noise and changes in visibility conditions. The experiments in simulation and real-world demonstrated that our proposed method is successful and resilient in navigating a low-cost underwater robot in unknown underwater environments. The implementation is made publicly available at //github.com/dartmouthrobotics/deeprl-uw-robot-navigation.
Generating realistic 3D worlds occupied by moving humans has many applications in games, architecture, and synthetic data creation. But generating such scenes is expensive and labor intensive. Recent work generates human poses and motions given a 3D scene. Here, we take the opposite approach and generate 3D indoor scenes given 3D human motion. Such motions can come from archival motion capture or from IMU sensors worn on the body, effectively turning human movement in a "scanner" of the 3D world. Intuitively, human movement indicates the free-space in a room and human contact indicates surfaces or objects that support activities such as sitting, lying or touching. We propose MIME (Mining Interaction and Movement to infer 3D Environments), which is a generative model of indoor scenes that produces furniture layouts that are consistent with the human movement. MIME uses an auto-regressive transformer architecture that takes the already generated objects in the scene as well as the human motion as input, and outputs the next plausible object. To train MIME, we build a dataset by populating the 3D FRONT scene dataset with 3D humans. Our experiments show that MIME produces more diverse and plausible 3D scenes than a recent generative scene method that does not know about human movement. Code and data will be available for research at //mime.is.tue.mpg.de.
Deep learning has shown great potential for modeling the physical dynamics of complex particle systems such as fluids (in Lagrangian descriptions). Existing approaches, however, require the supervision of consecutive particle properties, including positions and velocities. In this paper, we consider a partially observable scenario known as fluid dynamics grounding, that is, inferring the state transitions and interactions within the fluid particle systems from sequential visual observations of the fluid surface. We propose a differentiable two-stage network named NeuroFluid. Our approach consists of (i) a particle-driven neural renderer, which involves fluid physical properties into the volume rendering function, and (ii) a particle transition model optimized to reduce the differences between the rendered and the observed images. NeuroFluid provides the first solution to unsupervised learning of particle-based fluid dynamics by training these two models jointly. It is shown to reasonably estimate the underlying physics of fluids with different initial shapes, viscosity, and densities. It is a potential alternative approach to understanding complex fluid mechanics, such as turbulence, that are difficult to model using traditional methods of mathematical physics.
Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While these contrastive methods mainly focus on generating invariant global representations at the image-level under semantic-preserving transformations, they are prone to overlook spatial consistency of local representations and therefore have a limitation in pretraining for localization tasks such as object detection and instance segmentation. Moreover, aggressively cropped views used in existing contrastive methods can minimize representation distances between the semantically different regions of a single image. In this paper, we propose a spatially consistent representation learning algorithm (SCRL) for multi-object and location-specific tasks. In particular, we devise a novel self-supervised objective that tries to produce coherent spatial representations of a randomly cropped local region according to geometric translations and zooming operations. On various downstream localization tasks with benchmark datasets, the proposed SCRL shows significant performance improvements over the image-level supervised pretraining as well as the state-of-the-art self-supervised learning methods.
This work addresses a novel and challenging problem of estimating the full 3D hand shape and pose from a single RGB image. Most current methods in 3D hand analysis from monocular RGB images only focus on estimating the 3D locations of hand keypoints, which cannot fully express the 3D shape of hand. In contrast, we propose a Graph Convolutional Neural Network (Graph CNN) based method to reconstruct a full 3D mesh of hand surface that contains richer information of both 3D hand shape and pose. To train networks with full supervision, we create a large-scale synthetic dataset containing both ground truth 3D meshes and 3D poses. When fine-tuning the networks on real-world datasets without 3D ground truth, we propose a weakly-supervised approach by leveraging the depth map as a weak supervision in training. Through extensive evaluations on our proposed new datasets and two public datasets, we show that our proposed method can produce accurate and reasonable 3D hand mesh, and can achieve superior 3D hand pose estimation accuracy when compared with state-of-the-art methods.
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191