ProbIBR: Fast Image-Based Rendering with Learned Probability-Guided Sampling.

We present a general, fast, and practical solution for interpolating novel views of diverse real-world scenes given a sparse set of nearby views. Existing generic novel view synthesis methods rely on time-consuming scene geometry pre-computation or redundant sampling of the entire space for neural volumetric rendering, limiting the overall efficiency. Instead, we incorporate learned MVS priors into the neural volume rendering pipeline while improving the rendering efficiency by reducing sampling points under the guidance of depth probability distributions. Specifically, fewer but important points are sampled under the guidance of depth probability distributions extracted from the learned MVS architecture. Based on the learned probability-guided sampling, we develop a sophisticated neural volume rendering module that effectively integrates source view information with the learned scene structures. We further propose confidence-aware refinement to improve the rendering results in uncertain, occluded, and unreferenced regions. Moreover, we build a four-view camera system for holographic display and provide a real-time version of our framework for free-viewpoint experience, where novel view images of a spatial resolution of 512×512 can be rendered at around 20 fps on a single GTX 3090 GPU. Experiments show that our method achieves 15 to 40 times faster rendering compared to state-of-the-art baselines, with strong generalization capacity and comparable high-quality novel view synthesis performance.

Metadherin orchestrates PKA and PKM2 to activate ß-catenin signaling in podocytes during proteinuric chronic kidney disease.

Podocyte damage is the major cause of glomerular injury and proteinuria in multiple chronic kidney diseases. Metadherin (MTDH) is involved in podocyte apoptosis and promotes renal tubular injury in mouse models of diabetic nephropathy and renal fibrosis; however, its role in podocyte injury and proteinuria needs further exploration. Here, we show that MTDH was induced in the glomerular podocytes of patients with proteinuric chronic kidney disease and correlated with proteinuria. Podocyte-specific knockout of MTDH in mice reversed proteinuria, attenuated podocyte injury, and prevented glomerulosclerosis after advanced oxidation protein products challenge or adriamycin injury. Furthermore, specific knockout of MTDH in podocytes repressed ß-catenin phosphorylation at the Ser675 site and inhibited its downstream target gene transcription. Mechanistically, on the one hand, MTDH increased cAMP and then activated protein kinase A (PKA) to induce ß-catenin phosphorylation at the Ser675 site, facilitating the nuclear translocation of MTDH and ß-catenin; on the other hand, MTDH induced the deaggregation of pyruvate kinase M2 (PKM2) tetramers and promoted PKM2 monomers to enter the nucleus. This cascade of events leads to the formation of the MTDH/PKM2/ß-catenin/CBP/TCF4 transcription complex, thus triggering TCF4-dependent gene transcription. Inhibition of PKA activity by H-89 or blockade of PKM2 deaggregation by TEPP-46 abolished this cascade of events and disrupted transcription complex formation. These results suggest that MTDH induces podocyte injury and proteinuria by assembling the ß-catenin-mediated transcription complex by regulating PKA and PKM2 function.

Renal Fibrosis Is Alleviated through Targeted Inhibition of IL-11-Induced Renal Tubular Epithelial-to-Mesenchymal Transition.

Renal fibrosis is a pathologic process that leads to irreversible renal failure without effective treatment. Epithelial-to-mesenchymal transition (EMT) plays a key role in this process. The current study found that aberrant expression of IL-11 is critically involved in tubular EMT. IL-11 and its receptor subunit alpha-1 (IL-11Rα1) were significantly induced in renal tubular epithelial cells (RTECs) in unilateral ureteral obstruction (UUO) kidneys, co-localized with transforming growth factor-ß1. IL-11 knockdown ameliorated UUO-induced renal fibrosis in vivo and transforming growth factor-ß1-induced EMT in vitro. IL-11 intervention directly induced the transdifferentiation of RTECs to the mesenchymal phenotype and increased the synthesis of profibrotic mediators. The EMT response induced by IL-11 was dependent on the sequential activation of STAT3 and extracellular signal-regulated kinase 1/2 signaling pathways and the up-regulation of metadherin in RTECs. Micheliolide (MCL) competitively inhibited the binding of IL-11 with IL-11Rα1, suppressing the activation of STAT3 and extracellular signal-regulated kinase 1/2-metadherin pathways, ultimately inhibiting renal tubular EMT and interstitial fibrosis induced by IL-11. In addition, treatment with dimethylaminomicheliolide, a pro-drug of MCL for in vivo use, significantly ameliorated renal fibrosis exacerbated by IL-11 in the UUO model. These findings suggest that IL-11 is a promising target in renal fibrosis and that MCL/dimethylaminomicheliolide exerts its antifibrotic effect by suppressing IL-11/IL-11Rα1 interaction and blocking its downstream effects.

HVTR++: Image and Pose Driven Human Avatars using Hybrid Volumetric-Textural Rendering.

Recent neural rendering methods have made great progress in generating photorealistic human avatars. However, these methods are generally conditioned only on low-dimensional driving signals (e.g., body poses), which are insufficient to encode the complete appearance of a clothed human. Hence they fail to generate faithful details. To address this problem, we exploit driving view images (e.g., in telepresence systems) as additional inputs. We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR++), which synthesizes 3D human avatars from arbitrary driving poses and views while staying faithful to appearance details efficiently and at high quality. First, we learn to encode the driving signals of pose and view image on a dense UV manifold of the human body surface and extract UV-aligned features, preserving the structure of a skeleton-based parametric model. To handle complicated motions (e.g., self-occlusions), we then leverage the UV-aligned features to construct a 3D volumetric representation based on a dynamic neural radiance field. While this allows us to represent 3D geometry with changing topology, volumetric rendering is computationally heavy. Hence we employ only a rough volumetric representation using a pose- and image-conditioned downsampled neural radiance field (PID-NeRF), which we can render efficiently at low resolutions. In addition, we learn 2D textural features that are fused with rendered volumetric features in image space. The key advantage of our approach is that we can then convert the fused features into a high-resolution, high-quality avatar by a fast GAN-based textural renderer. We demonstrate that hybrid rendering enables HVTR++ to handle complicated motions, render high-quality avatars under user-controlled poses/shapes, and most importantly, be efficient at inference time. Our experimental results also demonstrate state-of-the-art quantitative results.

Robust and Accurate 3D Self-Portraits in Seconds.

In this paper, we propose an efficient method for robust and accurate 3D self-portraits using a single RGBD camera. Our method can generate detailed and realistic 3D self-portraits in seconds and shows the ability to handle subjects wearing extremely loose clothes. To achieve highly efficient and robust reconstruction, we propose PIFusion, which combines learning-based 3D recovery with volumetric non-rigid fusion to generate accurate sparse partial scans of the subject. Meanwhile, a non-rigid volumetric deformation method is proposed to continuously refine the learned shape prior. Moreover, a lightweight bundle adjustment algorithm is proposed to guarantee that all the partial scans can not only "loop" with each other but also remain consistent with the selected live key observations. Finally, to further generate realistic portraits, we propose non-rigid texture optimization to improve the texture quality. Additionally, we also contribute a benchmark for single-view 3D self-portrait reconstruction, an evaluation dataset that contains 10 single-view RGBD sequences of a self-rotating performer wearing various clothes and the corresponding ground-truth 3D models in the first frame of each sequence. The results and experiments based on this dataset show that the proposed method outperforms state-of-the-art methods on accuracy, efficiency, and generality.

PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction.

Modeling 3D humans accurately and robustly from a single image is very challenging, and the key for such an ill-posed problem is the 3D representation of the human models. To overcome the limitations of regular 3D representations, we propose Parametric Model-Conditioned Implicit Representation (PaMIR), which combines the parametric body model with the free-form deep implicit function. In our PaMIR-based reconstruction framework, a novel deep neural network is proposed to regularize the free-form deep implicit function using the semantic features of the parametric model, which improves the generalization ability under the scenarios of challenging poses and various clothing topologies. Moreover, a novel depth-ambiguity-aware training loss is further integrated to resolve depth ambiguities and enable successful surface detail reconstruction with imperfect body reference. Finally, we propose a body reference optimization method to improve the parametric model estimation accuracy and to enhance the consistency between the parametric model and the implicit function. With the PaMIR representation, our framework can be easily extended to multi-image input scenarios without the need of multi-camera calibration and pose synchronization. Experimental results demonstrate that our method achieves state-of-the-art performance for image-based 3D human reconstruction in the cases of challenging poses and clothing types.

Serum exosomal microRNA-766-3p expression is associated with poor prognosis of esophageal squamous cell carcinoma.

The aim was to analyze the association between exosomal microRNA (miR)-766-3p expression levels in serum and the prognosis of esophageal squamous cell carcinoma (ESCC). The serum global exosomal miRNA expression of ESCC patients was measured by microRNA microarray. Quantitative real-time PCR was used to analyze the expression levels of candidate miRNAs in both serum and tissues from ESCC patients. Wilcoxon tests were applied to evaluate clinical characteristics and their association with serum levels of exosomal miR-766-3p. A Cox regression model was used to identify prognostic factors. The effects of miR-766-3p expression on cell migration and invasion were examined using Transwell assays, and CCK-8 assays were carried out to measure cell proliferation. The TNM stage was associated with high serum exosomal miR-766-3p levels of ESCC patients (P = .030). Higher serum exosomal miR-766-3p expression levels were associated with poor prognosis (for overall survival, hazard ratio [HR] [95% confidence interval (CI)], 2.21 [1.00, 4.87]; for disease-free survival, HR [95% CI], 2.15 [1.01, 4.59]). However, we found no association between the expression of miR-766-3p in tissue and ESCC prognosis. In vitro results showed that miR-766-3p promotes cell migration and invasion, but not cell proliferation. By using dual-luciferase reporter assay, HOXA13 was confirmed as a direct target gene of miR-766-3p. The ESCC patients with highly expressed serum exosomal miR-766-3p had a significantly worse survival. Therefore, serum exosomal miR-766-3p could serve as a prognostic marker for the assessment of ESCC.

DoubleFusion: Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor.

We propose DoubleFusion, a new real-time system that combines volumetric non-rigid reconstruction with data-driven template fitting to simultaneously reconstruct detailed surface geometry, large non-rigid motion and the optimized human body shape from a single depth camera. One of the key contributions of this method is a double-layer representation consisting of a complete parametric body model inside, and a gradually fused detailed surface outside. A pre-defined node graph on the body parameterizes the non-rigid deformations near the body, and a free-form dynamically changing graph parameterizes the outer surface layer far from the body, which allows more general reconstruction. We further propose a joint motion tracking method based on the double-layer representation to enable robust and fast motion tracking performance. Moreover, the inner parametric body is optimized online and forced to fit inside the outer surface layer as well as the live depth input. Overall, our method enables increasingly denoised, detailed and complete surface reconstructions, fast motion tracking performance and plausible inner body shape reconstruction in real-time. Experiments and comparisons show improved fast motion tracking and loop closure performance on more challenging scenarios. Two extended applications including body measurement and shape retargeting show the potential of our system in terms of practical use.