We present radiance field propagation (RFP), a novel approach to segmenting objects in 3D during reconstruction given only unlabeled multi-view images of a scene. RFP is derived from emerging neural radiance field-based techniques, which jointly encodes semantics with appearance and geometry. The core of our method is a novel propagation strategy for individual objects' radiance fields with a bidirectional photometric loss, enabling an unsupervised partitioning of a scene into salient or meaningful regions corresponding to different object instances. To better handle complex scenes with multiple objects and occlusions, we further propose an iterative expectation-maximization algorithm to refine object masks. RFP is one of the first unsupervised approach for tackling 3D real scene object segmentation for neural radiance field (NeRF) without any supervision, annotations, or other cues such as 3D bounding boxes and prior knowledge of object class. Experiments demonstrate that RFP achieves feasible segmentation results that are more accurate than previous unsupervised image/scene segmentation approaches, and are comparable to existing supervised NeRF-based methods. The segmented object representations enable individual 3D object editing operations.
相關內容
Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. In this direction, we explore the tasks of 3D human semantic-, instance- and multi-human body-part segmentation. Few works have attempted to directly segment humans in point clouds (or depth maps), which is largely due to the lack of training data on humans interacting with 3D scenes. We address this challenge and propose a framework for synthesizing virtual humans in realistic 3D scenes. Synthetic point cloud data is attractive since the domain gap between real and synthetic depth is small compared to images. Our analysis of different training schemes using a combination of synthetic and realistic data shows that synthetic data for pre-training improves performance in a wide variety of segmentation tasks and models. We further propose the first end-to-end model for 3D multi-human body-part segmentation, called Human3D, that performs all the above segmentation tasks in a unified manner. Remarkably, Human3D even outperforms previous task-specific state-of-the-art methods. Finally, we manually annotate humans in test scenes from EgoBody to compare the proposed training schemes and segmentation models.
Point clouds captured by scanning devices are often incomplete due to occlusion. Point cloud completion aims to predict the complete shape based on its partial input. Existing methods can be classified into supervised and unsupervised methods. However, both of them require a large number of 3D complete point clouds, which are difficult to capture. In this paper, we propose Cross-PCC, an unsupervised point cloud completion method without requiring any 3D complete point clouds. We only utilize 2D images of the complete objects, which are easier to capture than 3D complete and clean point clouds. Specifically, to take advantage of the complementary information from 2D images, we use a single-view RGB image to extract 2D features and design a fusion module to fuse the 2D and 3D features extracted from the partial point cloud. To guide the shape of predicted point clouds, we project the predicted points of the object to the 2D plane and use the foreground pixels of its silhouette maps to constrain the position of the projected points. To reduce the outliers of the predicted point clouds, we propose a view calibrator to move the points projected to the background into the foreground by the single-view silhouette image. To the best of our knowledge, our approach is the first point cloud completion method that does not require any 3D supervision. The experimental results of our method are superior to those of the state-of-the-art unsupervised methods by a large margin. Moreover, compared to some supervised methods, our method achieves similar performance. We will make the source code publicly available at //github.com/ltwu6/cross-pcc.
We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training. While NeRF is usually trained with ground-truth camera poses, multiple extensions have been proposed to reduce the need for this expensive supervision. Nonetheless, most of these methods still struggle in complex settings with large camera movements, and are restricted to single scenes, i.e. they cannot be trained on a collection of scenes depicting the same object category. To address these issues, our method uses an analysis by synthesis approach, combining a conditional NeRF with a viewpoint predictor and a scene encoder in order to produce self-supervised reconstructions for whole object categories. Rather than focusing on high fidelity reconstruction, we target efficient and accurate viewpoint prediction in complex scenarios, e.g. 360{\deg} rotation on real data. Our model shows competitive results on synthetic and real datasets, both for single scenes and multi-instance collections.
Generative models have shown great promise in synthesizing photorealistic 3D objects, but they require large amounts of training data. We introduce SinGRAF, a 3D-aware generative model that is trained with a few input images of a single scene. Once trained, SinGRAF generates different realizations of this 3D scene that preserve the appearance of the input while varying scene layout. For this purpose, we build on recent progress in 3D GAN architectures and introduce a novel progressive-scale patch discrimination approach during training. With several experiments, we demonstrate that the results produced by SinGRAF outperform the closest related works in both quality and diversity by a large margin.
Virtual reality and augmented reality (XR) bring increasing demand for 3D content. However, creating high-quality 3D content requires tedious work that a human expert must do. In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate the ability to generate a plausible 3D object with 360{\deg} views that correspond well with the given reference image. By conditioning on the reference image, our model can fulfill the everlasting curiosity for synthesizing novel views of objects from images. Our technique sheds light on a promising direction of easing the workflows for 3D artists and XR designers. We propose a novel framework, dubbed NeuralLift-360, that utilizes a depth-aware neural radiance representation (NeRF) and learns to craft the scene guided by denoising diffusion models. By introducing a ranking loss, our NeuralLift-360 can be guided with rough depth estimation in the wild. We also adopt a CLIP-guided sampling strategy for the diffusion prior to provide coherent guidance. Extensive experiments demonstrate that our NeuralLift-360 significantly outperforms existing state-of-the-art baselines. Project page: //vita-group.github.io/NeuralLift-360/
Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and improve subsequent image processing tasks. Initial algorithms for unsupervised superpixel generation solely relied on local cues without prioritizing significant edges over arbitrary ones. On the other hand, more recent methods based on unsupervised deep learning either fail to properly address the trade-off between superpixel edge adherence and compactness or lack control over the generated number of superpixels. By using random images with strong spatial correlation as input, \ie, blurred noise images, in a non-convolutional image decoder we can reduce the expected number of contrasts and enforce smooth, connected edges in the reconstructed image. We generate edge-sparse pixel embeddings by encoding additional spatial information into the piece-wise smooth activation maps from the decoder's last hidden layer and use a standard clustering algorithm to extract high quality superpixels. Our proposed method reaches state-of-the-art performance on the BSDS500, PASCAL-Context and a microscopy dataset.
Convolution Neural Networks (CNNs) have been used in various fields and are showing demonstrated excellent performance, especially in Single-Image Super Resolution (SISR). However, recently, CNN-based SISR has numerous parameters and computational costs for obtaining better performance. As one of the methods to make the network efficient, Knowledge Distillation (KD) which optimizes the performance trade-off by adding a loss term to the existing network architecture is currently being studied. KD for SISR is mainly proposed as a feature distillation (FD) to minimize L1-distance loss of feature maps between teacher and student networks, but it does not fully take into account the amount and importance of information that the student can accept. In this paper, we propose a feature-based adaptive contrastive distillation (FACD) method for efficiently training lightweight SISR networks. We show the limitations of the existing feature-distillation (FD) with L1-distance loss, and propose a feature-based contrastive loss that maximizes the mutual information between the feature maps of the teacher and student networks. The experimental results show that the proposed FACD improves not only the PSNR performance of the entire benchmark datasets and scales but also the subjective image quality compared to the conventional FD approach.
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGRM), designed to model temporal relations and dependencies between video frames at various time spans. In particular, we capture and model temporal relations via constructing multi-level dilated temporal graphs where the nodes represent frames from different moments in video. Moreover, to enhance temporal reasoning ability of the proposed model, an auxiliary self-supervised task is proposed to encourage the dilated temporal graph reasoning module to find and correct wrong temporal relations in videos. Our DTGRM model outperforms state-of-the-art action segmentation models on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset. The code is available at //github.com/redwang/DTGRM.
Multi-view networks are ubiquitous in real-world applications. In order to extract knowledge or business value, it is of interest to transform such networks into representations that are easily machine-actionable. Meanwhile, network embedding has emerged as an effective approach to generate distributed network representations. Therefore, we are motivated to study the problem of multi-view network embedding, with a focus on the characteristics that are specific and important in embedding this type of networks. In our practice of embedding real-world multi-view networks, we identify two such characteristics, which we refer to as preservation and collaboration. We then explore the feasibility of achieving better embedding quality by simultaneously modeling preservation and collaboration, and propose the mvn2vec algorithms. With experiments on a series of synthetic datasets, an internal Snapchat dataset, and two public datasets, we further confirm the presence and importance of preservation and collaboration. These experiments also demonstrate that better embedding can be obtained by simultaneously modeling the two characteristics, while not over-complicating the model or requiring additional supervision.
In this paper, we propose the joint learning attention and recurrent neural network (RNN) models for multi-label classification. While approaches based on the use of either model exist (e.g., for the task of image captioning), training such existing network architectures typically require pre-defined label sequences. For multi-label classification, it would be desirable to have a robust inference process, so that the prediction error would not propagate and thus affect the performance. Our proposed model uniquely integrates attention and Long Short Term Memory (LSTM) models, which not only addresses the above problem but also allows one to identify visual objects of interests with varying sizes without the prior knowledge of particular label ordering. More importantly, label co-occurrence information can be jointly exploited by our LSTM model. Finally, by advancing the technique of beam search, prediction of multiple labels can be efficiently achieved by our proposed network model.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191