Chenghong Li

In this era, the success of large language models and text-to-image models can be attributed to the driving force of large-scale datasets. However, in the realm of 3D vision, while significant progress has been achieved in object-centric tasks through large-scale datasets like Objaverse and MVImgNet, human-centric tasks have seen limited advancement, largely due to the absence of a comparable large-scale human dataset. To bridge this gap, we present MVHumanNet++, a dataset that comprises multi-view human action sequences of 4,500 human identities. The primary focus of our work is on collecting human data that features a large number of diverse identities and everyday clothing using multi-view human capture systems, which facilitates easily scalable data collection. Our dataset contains 9,000 daily outfits, 60,000 motion sequences and 645 million frames with extensive annotations, including human masks, camera parameters, 2D and 3D keypoints, SMPL/SMPLX parameters, and corresponding textual descriptions. Additionally, the proposed MVHumanNet++ dataset is enhanced with newly processed normal maps and depth maps, significantly expanding its applicability and utility for advanced human-centric research. To explore the potential of our proposed MVHumanNet++ dataset in various 2D and 3D visual tasks, we conducted several pilot studies to demonstrate the performance improvements and effective applications enabled by the scale provided by MVHumanNet++. As the current largest-scale 3D human dataset, we hope that the release of MVHumanNet++ dataset with annotations will foster further innovations in the domain of 3D human-centric tasks at scale. MVHumanNet++ is publicly available at https://kevinlee09.github.io/research/MVHumanNet++/.

Neural implicit functions have brought impressive advances to the state-of-the-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen images with complex cloth deformation and body poses. In this work, we present GarVerseLOD, a new dataset and framework that paves the way to achieving unprecedented robustness in high-fidelity 3D garment reconstruction from a single unconstrained image. Inspired by the recent success of large generative models, we believe that one key to addressing the generalization challenge lies in the quantity and quality of 3D garment data. Towards this end, GarVerseLOD collects 6,000 high-quality cloth models with fine-grained geometry details manually created by professional artists. In addition to the scale of training data, we observe that having disentangled granularities of geometry can play an important role in boosting the generalization capability and inference accuracy of the learned model. We hence craft GarVerseLOD as a hierarchical dataset with levels of details (LOD) , spanning from detail-free stylized shape to pose-blended garment with pixel-aligned details. This allows us to make this highly under-constrained problem tractable by factorizing the inference into easier tasks, each narrowed down with smaller searching space. To ensure GarVerseLOD can generalize well to in-the-wild images, we propose a novel labeling paradigm based on conditional diffusion models to generate extensive paired images for each garment model with high photorealism. We evaluate our method on a massive amount of in-the-wild images. Experimental results demonstrate that GarVerseLOD can generate standalone garment pieces with significantly better quality than prior approaches while being robust against a large variation of pose, illumination, occlusion, and deformation. Code and dataset are available at garverselod.github.io.

Eyebrows play a critical role in facial expression and appearance. Although the 3D digitization of faces is well explored, less attention has been drawn to 3D eyebrow modeling. In this work, we propose EMS, the first learning-based framework for single-view 3D eyebrow reconstruction. Following the methods of scalp hair reconstruction, we also represent the eyebrow as a set of fiber curves and convert the reconstruction to fibers growing problem. Three modules are then carefully designed: RootFinder firstly localizes the fiber root positions which indicate where to grow; OriPredictor predicts an orientation field in the 3D space to guide the growing of fibers; FiberEnder is designed to determine when to stop the growth of each fiber. Our OriPredictor directly borrows the method used in hair reconstruction. Considering the differences between hair and eyebrows, both RootFinder and FiberEnder are newly proposed. Specifically, to cope with the challenge that the root location is severely occluded, we formulate root localization as a density map estimation task. Given the predicted density map, a density-based clustering method is further used for finding the roots. For each fiber, the growth starts from the root point and moves step by step until the ending, where each step is defined as an oriented line segment with a constant length according to the predicted orientation field. To determine when to end, a pixel-aligned RNN architecture is designed to form a binary classifier, which outputs stop or not for each growing step. To support the training of all proposed networks, we build the first 3D synthetic eyebrow dataset that contains 400 high-quality eyebrow models manually created by artists. Extensive experiments have demonstrated the effectiveness of the proposed EMS pipeline on a variety of different eyebrow styles and lengths, ranging from short and sparse to long bushy eyebrows.

We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images, for novel view synthesis. Previous solutions, such as pixelNeRF, rely only on pixel-aligned features and suffer from feature ambiguity issues. As a result, they struggle with the disentanglement of geometry and appearance, leading to implausible geometries and blurry results. To address this challenge, we propose to incorporate explicit geometry reasoning and combine it with pixel-aligned features for radiance field prediction. Specifically, in addition to pixel-aligned features, we further constrain the radiance field learning to be conditioned on i) voxel-aligned features learned from a coarse volumetric grid and ii) fine surface-aligned features extracted from a regressed point cloud. We show that the introduction of such geometry-aware features helps to achieve a better disentanglement between appearance and geometry, i.e. recovering more accurate geometries and synthesizing higher quality images of novel views. Extensive experiments against state-of-the-art methods on ShapeNet benchmarks demonstrate the superiority of our approach for single-image novel view synthesis.

BACKGROUND: Survivors of childhood cancer are at significant risk for serious chronic health conditions and subsequent cancers because of their prior treatment exposures. However, little is known about survivors' perceptions of their future health risks. METHODS: This study examined self‐reported levels of concern about future health and subsequent cancer in 15,620 adult survivors of childhood cancer (median age, 26 years; median time since diagnosis, 17 years) and 3991 siblings in the Childhood Cancer Survivor Study. The prevalence of concerns was compared between survivors and siblings, and the impact of participant characteristics and treatment exposures on concerns was examined with multivariable modified Poisson regression to estimate relative risks (RRs) and 95% confidence intervals (CIs). RESULTS: A substantial proportion of survivors were not concerned about their future health (31%) or developing cancer (40%). The prevalence of concern in survivors was modestly higher (RR for future health, 1.12; 95% CI, 1.09‐1.15) or similar (RR for subsequent cancer, 1.02; 95% CI, 0.99‐1.05) in comparison with siblings. Survivors exposed to high doses of radiation (≥20 Gy) were more likely to report concern (RR for future health, 1.13; 95% CI, 1.09‐1.16; RR for subsequent cancer, 1.14; 95% CI, 1.10‐1.18), but 35% of these high‐risk survivors were not concerned about developing cancer, and 24% were not concerned about their future health. CONCLUSIONS: A substantial subgroup of survivors were unconcerned about their future health and subsequent cancer risks, even after exposure to treatments associated with increased risk. These survivors may be less likely to engage in beneficial screening and risk‐reduction activities. Cancer 2018. © 2018 American Cancer Society .

Purpose: Analysis of biological samples in large cohort studies may provide insight into the mechanism of, and risk factors for, disease onset and progression.Methods: This study describes the methods used to collect biological samples from a large multi‐center cohort of childhood cancer survivors and siblings of childhood cancer survivors and evaluates the predictors of a positive response among these individuals.Results: Among survivors, female sex, white race/ethnicity, college graduation, never smoking, accessing the healthcare system in the past 2 years, and having a second malignant neoplasm were the strongest predictors of returning a sample. Among siblings, a similar demographic profile defined those likely to submit the requested sample.Conclusion: To reduce selection bias and increase the value of these samples for future analysis, additional phone calls and reminders targeting non‐responders are needed to improve response rates among those least likely to respond to a single mailed request. Pediatr Blood Cancer 2010;55:165–170.

We present a throughput-driven partitioning algorithm and a throughput-preserving merging algorithm for the high-level physical synthesis of latency-insensitive (LI) systems. These two algorithms are integrated along with a published floorplanner [5] in a new iterative physical synthesis flow to optimize system throughput and reduce area occupation. The partitioning algorithm performs bottom-up clustering of the internal logic of a given IP core to divide it into smaller ones, each of which has no combinational path from input to output and thus is legal for LI-interface encapsulation. Applying this algorithm to cores on critical feedback loops optimizes their length and in turn enables throughput optimization via the subsequent floorplanning. The merging algorithm reduces the number of cores on non-critical loops, lowering the overall area taken by LI interfaces without hurting the system throughput. Experimental results on a large system-on-chip design show a 16.7% speedup in system throughput and a 2.1% reduction in area occupation.

Latency-insensitive design is a methodology for system-on-chip (SoC) design that simplifies the reuse of intellectual property cores and the implementation of the communication among them. This simplification is based on a system-level protocol that decouples the intracore logic design from the design of the intercore communication channels. Each core is encapsulated within a shell, a synthesized logic block that dynamically controls its operation to interface it with the rest of the SoC and absorb any latency variations on its I/O signals. In particular, a shell stalls a core whenever new valid data are not available on the input channels or a downlink core has requested a delay in the data production on the output channels. We study how knowledge about the internal logic structure of a core can be applied to the design of its shell to improve the overall system-level performance by avoiding unnecessary local stalling. We introduce the notion of functional independence condition (FIC) and present a novel circuit design of a generic shell template that can leverage FIC. We propose a procedure for the logic synthesis of a FIC-shell instance that is only based on the analysis of the intracore logic and does not require any input from the designers. Finally, we present a comprehensive experimental analysis that shows the performance benefits and limited design overhead of the proposed technique. This includes the semicustom design of an SoC, an ultrawideband baseband transmitter, using a 90-nm industrial standard cell library.