WildAvatar: Web-scale In-the-wild Video Dataset for 3D Avatar Creation

Existing human datasets for avatar creation are typically limited to laboratory environments, wherein high-quality annotations (e.g., SMPL estimation from 3D scans or multi-view images) can be ideally provided. However, their annotating requirements are impractical for real-world images or videos, posing challenges toward real-world applications on current avatar creation methods. To this end, we propose the WildAvatar dataset, a web-scale in-the-wild human avatar creation dataset extracted from YouTube, with $10,000+$ different human subjects and scenes. WildAvatar is at least $10\times$ richer than previous datasets for 3D human avatar creation. We evaluate several state-of-the-art avatar creation methods on our dataset, highlighting the unexplored challenges in real-world applications on avatar creation. We also demonstrate the potential for generalizability of avatar creation methods, when provided with data at scale. We will publicly release our data source links and annotations, to push forward 3D human avatar creation and other related fields for real-world applications.

Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields

Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D descriptors for decoding novel views. However, existing methods show limited generalization ability in challenging conditions due to inaccurate geometry, sub-optimal descriptors, and decoding strategies. We address these issues point by point. First, we find the variance-based cost volume exhibits failure patterns as the features of pixels corresponding to the same point can be inconsistent across different views due to occlusions or reflections. We introduce an Adaptive Cost Aggregation (ACA) approach to amplify the contribution of consistent pixel pairs and suppress inconsistent ones. Unlike previous methods that solely fuse 2D features into descriptors, our approach introduces a Spatial-View Aggregator (SVA) to incorporate 3D context into descriptors through spatial and inter-view interaction. When decoding the descriptors, we observe the two existing decoding strategies excel in different areas, which are complementary. A Consistency-Aware Fusion (CAF) strategy is proposed to leverage the advantages of both. We incorporate the above ACA, SVA, and CAF into a coarse-to-fine framework, termed Geometry-aware Reconstruction and Fusion-refined Rendering (GeFu). GeFu attains state-of-the-art performance across multiple datasets. Code is available at https://github.com/TQTQliu/GeFu .

Neural Video Depth Stabilizer

Video depth estimation aims to infer temporally consistent depth. Some methods achieve temporal consistency by finetuning a single-image depth model during test time using geometry and re-projection constraints, which is inefficient and not robust. An alternative approach is to learn how to enforce temporal consistency from data, but this requires well-designed models and sufficient video depth data. To address these challenges, we propose a plug-and-play framework called Neural Video Depth Stabilizer (NVDS) that stabilizes inconsistent depth estimations and can be applied to different single-image depth models without extra effort. We also introduce a large-scale dataset, Video Depth in the Wild (VDW), which consists of 14,203 videos with over two million frames, making it the largest natural-scene video depth dataset to our knowledge. We evaluate our method on the VDW dataset as well as two public benchmarks and demonstrate significant improvements in consistency, accuracy, and efficiency compared to previous approaches. Our work serves as a solid baseline and provides a data foundation for learning-based video depth models. We will release our dataset and code for future research.

Diffusion-Augmented Depth Prediction with Sparse Annotations

Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity of annotations makes the task challenging. Supervised models produce concave objects due to insufficient structural information. They overfit to valid pixels and fail to restore spatial structures. Self-supervised methods are proposed for the problem. Their robustness is limited by pose estimation, leading to erroneous results in natural scenes. In this paper, we propose a supervised framework termed Diffusion-Augmented Depth Prediction (DADP). We leverage the structural characteristics of diffusion model to enforce depth structures of depth models in a plug-and-play manner. An object-guided integrality loss is also proposed to further enhance regional structure integrality by fetching objective information. We evaluate DADP on three driving benchmarks and achieve significant improvements in depth structures and robustness. Our work provides a new perspective on depth estimation with sparse annotations in autonomous driving scenes.

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods,DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS.

Application of attention-based Siamese composite neural network in medical image recognition

Medical image recognition often faces the problem of insufficient data in practical applications. Image recognition and processing under few-shot conditions will produce overfitting, low recognition accuracy, low reliability and insufficient robustness. It is often the case that the difference of characteristics is subtle, and the recognition is affected by perspectives, background, occlusion and other factors, which increases the difficulty of recognition. Furthermore, in fine-grained images, the few-shot problem leads to insufficient useful feature information in the images. Considering the characteristics of few-shot and fine-grained image recognition, this study has established a recognition model based on attention and Siamese neural network. Aiming at the problem of few-shot samples, a Siamese neural network suitable for classification model is proposed. The Attention-Based neural network is used as the main network to improve the classification effect. Covid- 19 lung samples have been selected for testing the model. The results show that the less the number of image samples are, the more obvious the advantage shows than the ordinary neural network.

Adaptive De-noising of Photoacoustic Signal and Image based on Modified Kalman Filter

As a burgeoning medical imaging method based on hybrid fusion of light and ultrasound, photoacoustic imaging (PAI) has demonstrated high potential in various biomedical applications recently, especially in revealing the functional and molecular information to improve diagnostic accuracy. However, stemming from weak amplitude and unavoidable random noise, caused by limited laser power and severe attenuation in deep tissue imaging, PA signals are usually of low signal-to-noise ratio (SNR), and reconstructed PA images are of low quality. Despite that conventional Kalman Filter (KF) can remove Gaussian noise in time domain, it lacks adaptability in real-time estimating condition due to its fixed model. Moreover, KF-based de-noising algorithm has not been applied in PAI before. In this paper, we propose an adaptive Modified Kalman Filter (MKF) targeted at PAI de-noising by tuning system noise matrix Q and measurement noise matrix R in the conventional KF model. Additionally, in order to compensate the signal skewing caused by KF, we cascade the backward part of Rauch-Tung-Striebel smoother (BRTS), which also utilizes the newly determined Q. Finally, as a supplement, we add a commonly used differential filter to remove in-band reflection artifacts. Experimental results using phantom and ex vivo colorectal tissue are provided to prove the validity of the algorithm.

Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper.

Accelerated and Deep Expectation Maximization for One-Bit MIMO-OFDM Detection

In this paper we study the expectation maximization (EM) technique for one-bit MIMO-OFDM detection (OMOD). Arising from the recent interest in massive MIMO with one-bit analog-to-digital converters, OMOD is a massive-scale problem. EM is an iterative method that can exploit the OFDM structure to process the problem in a per-iteration efficient fashion. In this study we analyze the convergence rate of EM for a class of approximate maximum-likelihood OMOD formulations, or, in a broader sense, a class of problems involving regression from quantized data. We show how the SNR and channel conditions can have an impact on the convergence rate. We do so by making a connection between the EM and the proximal gradient methods in the context of OMOD. This connection also gives us insight to build new accelerated and/or inexact EM schemes. The accelerated scheme has faster convergence in theory, and the inexact scheme provides us with the flexibility to implement EM more efficiently, with convergence guarantee. Furthermore we develop a deep EM algorithm, wherein we take the structure of our inexact EM algorithm and apply deep unfolding to train an efficient structured deep net. Simulation results show that our accelerated exact/inexact EM algorithms run much faster than their standard EM counterparts, and that the deep EM algorithm gives promising detection and runtime performances.

Rethinking the Aligned and Misaligned Features in One-stage Object Detection

One-stage object detectors rely on a point feature to predict the detection results. However, the point feature often lacks the information of the whole object, thereby leading to a misalignment between the object and the point feature. Meanwhile, the classification and regression tasks are sensitive to different object regions, but their features are spatially aligned. Both of these two problems hinder the detection performance. In order to solve these two problems, we propose a simple and plug-in operator that can generate aligned and disentangled features for each task, respectively, without breaking the fully convolutional manner. By predicting two task-aware point sets that are located in each sensitive region, the proposed operator can align the point feature with the object and disentangle the two tasks from the spatial dimension. We also reveal an interesting finding of the opposite effect of the long-range skip connection for classification and regression. On the basis of the Object-Aligned and Task-disentangled operator (OAT), we propose OAT-Net, which explicitly exploits point-set features for accurate detection results. Extensive experiments on the MS-COCO dataset show that OAT can consistently boost different state-of-the-art one-stage detectors by $\sim$2 AP. Notably, OAT-Net with Res2Net-101-DCN backbone achieves 53.7 AP on the COCO test-dev.