We present a simple yet powerful neural network that implicitly represents and renders 3D objects and scenes only from 2D observations. The network models 3D geometries as a general radiance field, which takes a set of 2D images with camera poses and intrinsics as input, constructs an internal representation for each point of the 3D space, and then renders the corresponding appearance and geometry of that point viewed from an arbitrary position. The key to our approach is to learn local features for each pixel in 2D images and to then project these features to 3D points, thus yielding general and rich point representations. We additionally integrate an attention mechanism to aggregate pixel features from multiple 2D views, such that visual occlusions are implicitly taken into account. Extensive experiments demonstrate that our method can generate high-quality and realistic novel views for novel objects, unseen categories and challenging real-world scenes.
论文检索
输入标题、作者或关键词，从 1,612 篇学术成果中精准定位
In this paper, we abandon the dominant complex language model and rethink the linguistic learning process in the scene text recognition. Different from previous methods considering the visual and linguistic information in two separate structures, we propose a Visual Language Modeling Network (VisionLAN), which views the visual and linguistic information as a union by directly enduing the vision model with language capability. Specially, we introduce the text recognition of character-wise occluded feature maps in the training stage. Such operation guides the vision model to use not only the visual texture of characters, but also the linguistic information in visual context for recognition when the visual cues are confused (e.g. occlusion, noise, etc.). As the linguistic information is acquired along with visual features without the need of extra language model, VisionLAN significantly improves the speed by 39% and adaptively considers the linguistic information to enhance the visual features for accurate recognition. Furthermore, an Occlusion Scene Text (OST) dataset is proposed to evaluate the performance on the case of missing character-wise visual cues. The state of-the-art results on several benchmarks prove our effectiveness. Code and dataset are available at https://github.com/wangyuxin87/VisionLAN.
Model compression techniques are recently gaining explosive attention for obtaining efficient AI models for various real time applications. Channel pruning is one important compression strategy, and widely used in slimming various DNNs. Previous gate-based or importance-based pruning methods aim to remove channels whose "importance" are smallest. However, it remains unclear what criteria the channel importance should be measured on, leading to various channel selection heuristics. Some other sampling-based pruning methods deploy sampling strategy to train sub-nets, which often causes the training instability and the compressed model's degraded performance. In view of the research gaps, we present a new module named Gates with Differentiable Polarization (GDP), inspired by principled optimization ideas. GDP can be plugged before convolutional layers without bells and whistles, to control the on-and-off of each channel or whole layer block. During the training process, the polarization effect will drive a subset of gates to smoothly decrease to exactly zero, while other gates gradually stay away from zero by a large margin. When training terminates, those zero-gated channels can be painlessly removed, while other non-zero gates can be absorbed into the succeeding convolution kernel, causing completely no interruption to training nor damage to the trained model. Experiments conducted over CIFAR-10 and ImageNet datasets show that the proposed GDP algorithm achieves the state-of-the-art performance on various benchmark DNNs at a broad range of pruning ratios. We also apply GDP to DeepLabV3Plus-ResNet50 on the challenging Pascal VOC segmentation task, whose test performance sees no drop (even slightly improved) with over 60% FLOPs saving.
Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic activities and camera motion, we propose a multi-camera framework in which geometric constraints are embedded in the form of multi-view consistency during training via coarse 3D localization in a voxel grid and fine-grained offset regression. In this manner, we learn a joint distribution of proposals over multiple views. At inference time, our method operates on single RGB images. We outperform state-of-the-art techniques both on images that visually depart from those of standard benchmarks and on those of the classical Human3.6M dataset.
Inverting a Rolling Shutter Camera: Bring Rolling Shutter Images to High Framerate Global Shutter Video
PDF ↗Rolling shutter (RS) images can be viewed as the result of the row-wise combination of global shutter (GS) images captured by a virtual moving GS camera over the period of camera readout time. The RS effect brings tremendous difficulties for the downstream applications. In this paper, we propose to invert the above RS imaging mechanism, i.e., recovering a high framerate GS video from consecutive RS images to achieve RS temporal super-resolution (RSSR). This extremely challenging problem, e.g., recovering 1440 GS images from two 720-height RS images, is far from being solved end-to-end. To address this challenge, we exploit the geometric constraint in the RS camera model, thus achieving geometry-aware inversion. Specifically, we make three contributions in resolving the above difficulties: (i) formulating the bidirectional RS undistortion flows under the constant velocity motion model, (ii) building the connection between the RS undistortion flow and optical flow via a scaling operation, and (iii) developing a mutual conversion scheme between varying RS undistortion flows that correspond to different scanlines. Building upon these formulations, we propose the first RS temporal super-resolution network in a cascaded structure to extract high framerate global shutter video. Our method explores the underlying spatio-temporal geometric relationships within a deep learning framework, where no extra supervision besides the middle-scanline ground truth GS image is needed. Essentially, our method can be very efficient for explicit propagation to generate GS images under any scanline. Experimental results on both synthetic and real data show that our method can produce high-quality GS image sequences with rich details, outperforming state-of-the-art methods.
3D human pose estimation from monocular images is a highly ill-posed problem due to depth ambiguities and occlusions. Nonetheless, most existing works ignore these ambiguities and only estimate a single solution. In contrast, we generate a diverse set of hypotheses that represents the full posterior distribution of feasible 3D poses. To this end, we propose a normalizing flow based method that exploits the deterministic 3D-to-2D mapping to solve the ambiguous inverse 2D-to-3D problem. Additionally, uncertain detections and occlusions are effectively modeled by incorporating uncertainty information of the 2D detector as condition. Further keys to success are a learned 3D pose prior and a generalization of the best-of-M loss. We evaluate our approach on the two benchmark datasets Human3.6M and MPI-INF-3DHP, outperforming all comparable methods in most metrics. The implementation is available on GitHub.
Learning temporally consistent foreground opacity from videos, i.e., video matting, has drawn great attention due to the blossoming of video conferencing. Previous approaches are built on top of image matting models, which fail in maintaining the temporal coherence when being adapted to videos. They either utilize the optical flow to smooth frame-wise prediction, where the performance is dependent on the selected optical flow model; or naively combine feature maps from multiple frames, which does not model well the correspondence of pixels in adjacent frames. In this paper, we propose to enhance the temporal coherence by Consistency-Regularized Graph Neural Networks (CRGNN) with the aid of a synthesized video matting dataset. CRGNN utilizes Graph Neural Networks (GNN) to relate adjacent frames such that pixels or regions that are incorrectly predicted in one frame can be corrected by leveraging information from its neighboring frames. To generalize our model from synthesized videos to real-world videos, we propose a consistency regularization technique to enforce the consistency on the alpha and foreground when blending them with different backgrounds. To evaluate the efficacy of CRGNN, we further collect a real-world dataset with annotated alpha mattes. Compared with state-of-the-art methods that require hand-crafted trimaps or backgrounds for modeling training, CRGNN generates favorably results with the help of unlabeled real training dataset.
Arbitrary shape text detection is a challenging task due to the high complexity and variety of scene texts. In this work, we propose a novel adaptive boundary proposal network for arbitrary shape text detection, which can learn to directly produce accurate boundary for arbitrary shape text without any post-processing. Our method mainly consists of a boundary proposal model and an innovative adaptive boundary deformation model. The boundary proposal model constructed by multi-layer dilated convolutions is adopted to produce prior information (including classification map, distance field, and direction field) and coarse boundary proposals. The adaptive boundary deformation model is an encoder-decoder network, in which the encoder mainly consists of a Graph Convolutional Network (GCN) and a Recurrent Neural Network (RNN). It aims to perform boundary deformation in an iterative way for obtaining text instance shape guided by prior information from the boundary proposal model. In this way, our method can directly and efficiently generate accurate text boundaries without complex post-processing. Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method.
Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face representations susceptible to privacy leakage (b) it appears to contribute to bias in face recognition. However, existing bias mitigation approaches generally require end-to-end training and are unable to achieve high verification accuracy. Therefore, we present a descriptor-based adversarial de-biasing approach called `Protected Attribute Suppression System (PASS)'. PASS can be trained on top of descriptors obtained from any previously trained high-performing network to classify identities and simultaneously reduce encoding of sensitive attributes. This eliminates the need for end-to-end training. As a component of PASS, we present a novel discriminator training strategy that discourages a network from encoding protected attribute information. We show the efficacy of PASS to reduce gender and skintone information in descriptors from SOTA face recognition networks like Arcface. As a result, PASS descriptors outperform existing baselines in reducing gender and skintone bias on the IJB-C dataset, while maintaining a high verification accuracy.
Fast arbitrary neural style transfer has attracted widespread attention from academic, industrial and art communities due to its flexibility in enabling various applications. Existing solutions either attentively fuse deep style feature into deep content feature without considering feature distributions, or adaptively normalize deep content feature according to the style such that their global statistic information is matched. Although effective, leaving shallow feature unexplored or without locally considering feature statistics, they are prone to suffer from unnatural output with unpleasing local distortions. To alleviate this problem, in this paper, we propose a novel Adaptive Attention Normalization (AdaAttN) module to adaptively perform attentive normalization on per-point basis. Specifically, spatial attention score is learnt from both shallow and deep features of content and style images. Then per-point weighted statistics are calculated by regarding a style feature point as a distribution of attention-weighted output of all style feature points. Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics. Besides, a novel local feature loss is derived based on AdaAttN to enhance local visual quality. We also extend AdaAttN to be ready for video style transfer with slight modifications. Extensive experiments demonstrate that our method achieves state-of-the-art arbitrary image/video style transfer. Codes and models will be available.
The minimal geodesic models based on the Eikonal equations are capable of finding suitable solutions in various image segmentation scenarios. Existing geodesic-based segmentation approaches usually exploit the image features in conjunction with geometric regularization terms (such as curve length or elastica length) for computing geodesic paths. In this paper, we consider a more complicated problem: finding simple and closed geodesic curves which are imposed a convexity shape prior. The proposed approach relies on an orientation-lifting strategy, by which a planar curve can be mapped to an high-dimensional orientation space. The convexity shape prior serves as a constraint for the construction of local metrics. The geodesic curves in the lifted space then can be efficiently computed through the fast marching method. In addition, we introduce a way to incorporate region-based homogeneity features into the proposed geodesic model so as to solve the region-based segmentation issues with shape prior constraints.
Benchmark datasets that measure camera pose accuracy have driven progress in visual re-localisation research. To obtain poses for thousands of images, it is common to use a reference algorithm to generate pseudo ground truth. Popular choices include Structure-from-Motion (SfM) and Simultaneous-Localisation-and-Mapping (SLAM) using additional sensors like depth cameras if available. Re-localisation benchmarks thus measure how well each method replicates the results of the reference algorithm. This begs the question whether the choice of the reference algorithm favours a certain family of re-localisation methods. This paper analyzes two widely used re-localisation datasets and shows that evaluation outcomes indeed vary with the choice of the reference algorithm. We thus question common beliefs in the re-localisation literature, namely that learning-based scene coordinate regression outperforms classical feature-based methods, and that RGB-D- based methods outperform RGB-based methods. We argue that any claims on ranking re-localisation methods should take the type of the reference algorithm, and the similarity of the methods to the reference algorithm, into account.
Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the commonly reported validation split. This generated a distorted impression about the superiority of Pseudo-LiDAR-based (PL-based) approaches over methods working with RGB images only. Our first contribution consists in rectifying this view by pointing out and showing experimentally that the validation results published by PL-based methods are substantially biased. The source of the bias resides in an overlap between the KITTI3D object detection validation set and the training/validation sets used to train depth predictors feeding PL-based methods. Surprisingly, the bias remains also after geographically removing the overlap. This leaves the test set as the only reliable set for comparison, where published PL-based methods do not excel. Our second contribution brings PL-based methods back up in the ranking with the design of a novel deep architecture which introduces a 3D confidence prediction module. We show that 3D confidence estimation techniques derived from RGB-only 3D detection approaches can be successfully integrated into our framework and, more importantly, that improved performance can be obtained with a newly designed 3D confidence measure, leading to state-of-the-art performance on the KITTI3D benchmark.
Track Without Appearance: Learn Box and Tracklet Embedding With Local and Global Motion Patterns for Vehicle Tracking
PDF ↗Vehicle tracking is an essential task in the multi-object tracking (MOT) field. A distinct characteristic in vehicle tracking is that the trajectories of vehicles are fairly smooth in both the world coordinate and the image coordinate. Hence, models that capture motion consistencies are of high necessity. However, tracking with the standalone motion-based trackers is quite challenging because targets could get lost easily due to limited information, detection error and occlusion. Leveraging appearance information to assist object re-identification could resolve this challenge to some extent. However, doing so requires extra computation while appearance information is sensitive to occlusion as well. In this paper, we try to explore the significance of motion patterns for vehicle tracking without appearance information. We propose a novel approach that tackles the association issue for long-term tracking with the exclusive fully-exploited motion information. We address the tracklet embedding issue with the proposed reconstruct-to-embed strategy based on deep graph convolutional neural networks (GCN). Comprehensive experiments on the KITTI-car tracking dataset and UA-Detrac dataset show that the proposed method, though without appearance information, could achieve competitive performance with the state-of-the-art (SOTA) trackers. The source code will be available at https://github.com/GaoangW/LGMTracker.
As a fundamental building block in computer vision, edges can be categorised into four types according to the discontinuity in surface-Reflectance, Illumination, surface-Normal or Depth. While great progress has been made in detecting generic or individual types of edges, it remains under-explored to comprehensively study all four edge types together. In this paper, we propose a novel neural network solution, RINDNet, to jointly detect all four types of edges. Taking into consideration the distinct attributes of each type of edges and the relationship between them, RINDNet learns effective representations for each of them and works in three stages. In stage I, RINDNet uses a common backbone to extract features shared by all edges. Then in stage II it branches to prepare discriminative features for each edge type by the corresponding decoder. In stage III, an independent decision head for each type aggregates the features from previous stages to predict the initial results. Additionally, an attention module learns attention maps for all types to capture the underlying relations between them, and these maps are combined with initial results to generate the final edge detection results. For training and evaluation, we construct the first public benchmark, BSDS-RIND, with all four types of edges carefully annotated. In our experiments, RINDNet yields promising results in comparison with state-of-the-art methods. Additional analysis is presented in supplementary material.
The inverted index is one of the most commonly used structures for non-exhaustive nearest neighbor search on large-scale datasets. It allows a significant factor of acceleration by a reduced number of distance computations with only a small fraction of the database. In particular, the inverted index enables the product quantization (PQ) to learn their codewords in the residual vector space. The quantization error of the PQ can be substantially improved in such combination since the residual vector space is much more quantization-friendly thanks to their compact distribution compared to the original data. In this paper, we first raise an unremarked but crucial question; why the inverted index and the product quantizer are optimized separately even though they are closely related? For instance, changes on the inverted index distort the whole residual vector space. To address the raised question, we suggest a joint optimization of the coarse and fine quantizers by substituting the original objective of the coarse quantizer to end-to-end quantization distortion. Moreover, our method is generic and applicable to different combinations of coarse and fine quantizers such as inverted multi-index and optimized PQ.
For face texture completion, previous methods typically use some complete textures captured by multiview imaging systems or 3D scanners for supervised learning. This paper deals with a new challenging problem -- learning to complete invisible texture in a single face image without using any complete texture. We simply leverage a large corpus of face images of different subjects (e.\,g., FFHQ) to train a texture completion model in an unsupervised manner. To achieve this, we propose DSD-GAN, a novel deep neural network based method that applies two discriminators in UV map space and image space. These two discriminators work in a complementary manner to learn both facial structures and texture details. We show that their combination is essential to obtain high-fidelity results. Despite the network never sees any complete facial appearance, it is able to generate compelling full textures from single images.
RGB-D based 6D pose estimation has recently achieved remarkable progress, but still suffers from two major limitations: (1) ineffective representation of depth data and (2) insufficient integration of different modalities. This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way. It first introduces the Point Refinement Network (PRN) to polish 3D point clouds, recovering missing parts with noise removed. Subsequently, the Multi-Modal Fusion Graph Convolutional Network (MMF-GCN) is presented to strengthen RGB-D combination, which captures geometry-aware inter-modality correlation through local information propagation in the graph convolutional network. Extensive experiments are conducted on three widely used benchmarks, and state-of-the-art performance is reached. Besides, it is also shown that the proposed PRN and MMF-GCN modules are well generalized to other frameworks.
In many computer vision problems, it is desired to learn the effective visual data similarity such that the prediction accuracy can be enhanced. Deep Metric Learning (DML) methods have been actively studied to measure the data similarity. Pair-based and proxy-based losses are the two major paradigms in DML. However, pair-wise methods involve expensive training costs, while proxy-based methods are less accurate in characterizing the relationships between data points. In this paper, we provide a hybrid grouplet paradigm, which inherits the accurate pair-wise relationship in pair-based methods and the efficient training in proxy-based methods. Our method also equips a non-Euclidean space to DML, which employs a hierarchical representation manifold. More specifically, we propose a unified graph perspective --- different DML methods learn different local connecting patterns between data points. Based on the graph interpretation, we construct a flexible subset of data points, dubbed grouplet. Our grouplet doesn't require explicit pair-wise relationships, instead, we encode the data relationships in an optimal transport problem regarding the proxies, and solve this problem via a differentiable implicit layer to automatically determine the relationships. Extensive experimental results show that our method significantly outperforms state-of-the-art baselines on several benchmarks. The ablation studies also verify the effectiveness of our method.
This presentation addresses the problem of reconstructing a high-resolution image from multiple lower-resolution snapshots captured from slightly different viewpoints in space and time. Key challenges for solving this super-resolution problem include (i) aligning the input pictures with sub-pixel accuracy, (ii) handling raw (noisy) images for maximal faithfulness to native camera data, and (iii) designing/learning an image prior (regularizer) well suited to the task. We address these three challenges with a hybrid algorithm building on the insight from Wronski et al. that aliasing is an ally in this setting, with parameters that can be learned end to end, while retaining the interpretability of classical approaches to inverse problems. The effectiveness of our approach is demonstrated on synthetic and real image bursts, setting a new state of the art on several benchmarks and delivering excellent qualitative results on real raw bursts captured by smartphones and prosumer cameras.