arXiv subjects

Ying Feng

Publications and source records attributed to Ying Feng.

33 records · Page 2Linked to original sources

arXiv2023

HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

Recent text-to-3D methods employing diffusion models have made significant advancements in 3D human generation. However, these approaches face challenges due to the limitations of text-to-image diffusion models, which lack an understanding of 3D structures. Consequently, these methods struggle to achieve high-quality human generation, resulting in smooth geometry and cartoon-like appearances. In this paper, we propose HumanNorm, a novel approach for high-quality and realistic 3D human generation. The main idea is to enhance the model's 2D perception of 3D geometry by learning a normal-adapted diffusion model and a normal-aligned diffusion model. The normal-adapted diffusion model can generate high-fidelity normal maps corresponding to user prompts with view-dependent and body-aware text. The normal-aligned diffusion model learns to generate color images aligned with the normal maps, thereby transforming physical geometry details into realistic appearance. Leveraging the proposed normal diffusion model, we devise a progressive geometry generation strategy and a multi-step Score Distillation Sampling (SDS) loss to enhance the performance of 3D human generation. Comprehensive experiments substantiate HumanNorm's ability to generate 3D humans with intricate geometry and realistic appearances. HumanNorm outperforms existing text-to-3D methods in both geometry and texture quality. The project page of HumanNorm is https://humannorm.github.io/.

cs.CV↗

arXiv2023

Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detail

We present LoD-NeuS, an efficient neural representation for high-frequency geometry detail recovery and anti-aliased novel view rendering. Drawing inspiration from voxel-based representations with the level of detail (LoD), we introduce a multi-scale tri-plane-based scene representation that is capable of capturing the LoD of the signed distance function (SDF) and the space radiance. Our representation aggregates space features from a multi-convolved featurization within a conical frustum along a ray and optimizes the LoD feature volume through differentiable rendering. Additionally, we propose an error-guided sampling strategy to guide the growth of the SDF during the optimization. Both qualitative and quantitative evaluations demonstrate that our method achieves superior surface reconstruction and photorealistic view synthesis compared to state-of-the-art approaches.

cs.CV↗

arXiv2023

Improved Algorithms for White-Box Adversarial Streams

We study streaming algorithms in the white-box adversarial stream model, where the internal state of the streaming algorithm is revealed to an adversary who adaptively generates the stream updates, but the algorithm obtains fresh randomness unknown to the adversary at each time step. We incorporate cryptographic assumptions to construct robust algorithms against such adversaries. We propose efficient algorithms for sparse recovery of vectors, low rank recovery of matrices and tensors, as well as low rank plus sparse recovery of matrices, i.e., robust PCA. Unlike deterministic algorithms, our algorithms can report when the input is not sparse or low rank even in the presence of such an adversary. We use these recovery algorithms to improve upon and solve new problems in numerical linear algebra and combinatorial optimization on white-box adversarial streams. For example, we give the first efficient algorithm for outputting a matching in a graph with insertions and deletions to its edges provided the matching size is small, and otherwise we declare the matching size is large. We also improve the approximation versus memory tradeoff of previous work for estimating the number of non-zero elements in a vector and computing the matrix rank.

cs.DS↗

arXiv2023

HDR-NeRF: High Dynamic Range Neural Radiance Fields

We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. Using the HDR-NeRF, we are able to generate both novel HDR views and novel LDR views under different exposures. The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper. The radiance field encodes the scene radiance (values vary from 0 to +infty), which outputs the density and radiance of a ray by giving corresponding ray origin and ray direction. The tone mapper models the mapping process that a ray hitting on the camera sensor becomes a pixel value. The color of the ray is predicted by feeding the radiance and the corresponding exposure time into the tone mapper. We use the classic volume rendering technique to project the output radiance, colors, and densities into HDR and LDR images, while only the input LDR images are used as the supervision. We collect a new forward-facing HDR dataset to evaluate the proposed method. Experimental results on synthetic and real-world scenes validate that our method can not only accurately control the exposures of synthesized views but also render views with a high dynamic range.

cs.CV↗

arXiv2023

Local Implicit Ray Function for Generalizable Radiance Field Representation

We propose LIRF (Local Implicit Ray Function), a generalizable neural rendering approach for novel view rendering. Current generalizable neural radiance fields (NeRF) methods sample a scene with a single ray per pixel and may therefore render blurred or aliased views when the input views and rendered views capture scene content with different resolutions. To solve this problem, we propose LIRF to aggregate the information from conical frustums to construct a ray. Given 3D positions within conical frustums, LIRF takes 3D coordinates and the features of conical frustums as inputs and predicts a local volumetric radiance field. Since the coordinates are continuous, LIRF renders high-quality novel views at a continuously-valued scale via volume rendering. Besides, we predict the visible weights for each input view via transformer-based feature matching to improve the performance in occluded areas. Experimental results on real-world scenes validate that our method outperforms state-of-the-art methods on novel view rendering of unseen scenes at arbitrary scales.

cs.CV↗

arXiv2023

Inverting the Imaging Process by Learning an Implicit Camera Model

Representing visual signals with implicit coordinate-based neural networks, as an effective replacement of the traditional discrete signal representation, has gained considerable popularity in computer vision and graphics. In contrast to existing implicit neural representations which focus on modelling the scene only, this paper proposes a novel implicit camera model which represents the physical imaging process of a camera as a deep neural network. We demonstrate the power of this new implicit camera model on two inverse imaging tasks: i) generating all-in-focus photos, and ii) HDR imaging. Specifically, we devise an implicit blur generator and an implicit tone mapper to model the aperture and exposure of the camera's imaging process, respectively. Our implicit camera model is jointly learned together with implicit scene models under multi-focus stack and multi-exposure bracket supervision. We have demonstrated the effectiveness of our new model on a large number of test images and videos, producing accurate and visually appealing all-in-focus and high dynamic range images. In principle, our new implicit neural camera model has the potential to benefit a wide array of other inverse imaging tasks.

cs.CV↗

arXiv2023

NeAI: A Pre-convoluted Representation for Plug-and-Play Neural Ambient Illumination

Recent advances in implicit neural representation have demonstrated the ability to recover detailed geometry and material from multi-view images. However, the use of simplified lighting models such as environment maps to represent non-distant illumination, or using a network to fit indirect light modeling without a solid basis, can lead to an undesirable decomposition between lighting and material. To address this, we propose a fully differentiable framework named neural ambient illumination (NeAI) that uses Neural Radiance Fields (NeRF) as a lighting model to handle complex lighting in a physically based way. Together with integral lobe encoding for roughness-adaptive specular lobe and leveraging the pre-convoluted background for accurate decomposition, the proposed method represents a significant step towards integrating physically based rendering into the NeRF representation. The experiments demonstrate the superior performance of novel-view rendering compared to previous works, and the capability to re-render objects under arbitrary NeRF-style environments opens up exciting possibilities for bridging the gap between virtual and real-world scenes. The project and supplementary materials are available at https://yiyuzhuang.github.io/NeAI/.

cs.CV↗

arXiv2022

Composition based oxidation state prediction of materials using deep learning

Oxidation states are the charges of atoms after their ionic approximation of their bonds, which have been widely used in charge-neutrality verification, crystal structure determination, and reaction estimation. Currently only heuristic rules exist for guessing the oxidation states of a given compound with many exceptions. Recent work has developed machine learning models based on heuristic structural features for predicting the oxidation states of metal ions. However, composition based oxidation state prediction still remains elusive so far, which is more important in new material discovery for which the structures are not even available. This work proposes a novel deep learning based BERT transformer language model BERTOS for predicting the oxidation states of all elements of inorganic compounds given only their chemical composition. Our model achieves 96.82\% accuracy for all-element oxidation states prediction benchmarked on the cleaned ICSD dataset and achieves 97.61\% accuracy for oxide materials. We also demonstrate how it can be used to conduct large-scale screening of hypothetical material compositions for materials discovery.

cond-mat.mtrl-sci↗

arXiv2022

Hallucinated Neural Radiance Fields in the Wild

Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e., recovering a realistic NeRF at a different time of day from a group of tourism images. Existing solutions adopt NeRF with a controllable appearance embedding to render novel views under various conditions, but they cannot render view-consistent images with an unseen appearance. To solve this problem, we present an end-to-end framework for constructing a hallucinated NeRF, dubbed as Ha-NeRF. Specifically, we propose an appearance hallucination module to handle time-varying appearances and transfer them to novel views. Considering the complex occlusions of tourism images, we introduce an anti-occlusion module to decompose the static subjects for visibility accurately. Experimental results on synthetic data and real tourism photo collections demonstrate that our method can hallucinate the desired appearances and render occlusion-free images from different views. The project and supplementary materials are available at https://rover-xingyu.github.io/Ha-NeRF/.

cs.CV↗

arXiv2022

Stereo Unstructured Magnification: Multiple Homography Image for View Synthesis

This paper studies the problem of view synthesis with certain amount of rotations from a pair of images, what we called stereo unstructured magnification. While the multi-plane image representation is well suited for view synthesis with depth invariant, how to generalize it to unstructured views remains a significant challenge. This is primarily due to the depth-dependency caused by camera frontal parallel representation. Here we propose a novel multiple homography image (MHI) representation, comprising of a set of scene planes with fixed normals and distances. A two-stage network is developed for novel view synthesis. Stage-1 is an MHI reconstruction module that predicts the MHIs and composites layered multi-normal images along the normal direction. Stage-2 is a normal-blending module to find blending weights. We also derive an angle-based cost to guide the blending of multi-normal images by exploiting per-normal geometry. Compared with the state-of-the-art methods, our method achieves superior performance for view synthesis qualitatively and quantitatively, especially for cases when the cameras undergo rotations.

cs.CV↗

arXiv2020

For2For: Learning to forecast from forecasts

This paper presents a time series forecasting framework which combines standard forecasting methods and a machine learning model. The inputs to the machine learning model are not lagged values or regular time series features, but instead forecasts produced by standard methods. The machine learning model can be either a convolutional neural network model or a recurrent neural network model. The intuition behind this approach is that forecasts of a time series are themselves good features characterizing the series, especially when the modelling purpose is forecasting. It can also be viewed as a weighted ensemble method. Tested on the M4 competition dataset, this approach outperforms all submissions for quarterly series, and is more accurate than all but the winning algorithm for monthly series.

stat.ML↗

arXiv2014

Limits on Stellar Companions to Exoplanet Host Stars With Eccentric Planets

Though there are now many hundreds of confirmed exoplanets known, the binarity of exoplanet host stars is not well understood. This is particularly true of host stars which harbor a giant planet in a highly eccentric orbit since these are more likely to have had a dramatic dynamical history which transferred angular momentum to the planet. Here we present observations of four exoplanet host stars which utilize the excellent resolving power of the Differential Speckle Survey Instrument (DSSI) on the Gemini North telescope. Two of the stars are giants and two are dwarfs. Each star is host to a giant planet with an orbital eccentricity > 0.5 and whose radial velocity data contain a trend in the residuals to the Keplerian orbit fit. These observations rule out stellar companions 4-8 magnitudes fainter than the host star at passbands of 692nm and 880nm. The resolution and field-of-view of the instrument result in exclusion radii of 0.05-1.4 arcsecs which excludes stellar companions within several AU of the host star in most cases. We further provide new radial velocities for the HD 4203 system which confirm that the linear trend previously observed in the residuals is due to an additional planet. These results place dynamical constraints on the source of the planet's eccentricities, constraints on additional planetary companions, and informs the known distribution of multiplicity amongst exoplanet host stars.

astro-ph.EP↗

arXiv2013

f-Orthomorphisms and f-Linear Operators on the Order Dual of an f-Algebra

In this paper we consider the $f$-orthomorphisms and $f$-linear operators on the order dual of an $f$-algebra. In particular, when the $f$-algebra has the factorization property (not necessarily unital), we prove that the orthomorphisms, $f$-orthomorphisms and $f$-linear operators on the order dual are precisely the same class of operators.

math.FA↗

arXiv2013

The TRENDS High-Contrast Imaging Survey. II. Direct Detection of the HD 8375 Tertiary

We present the direct imaging detection of a faint tertiary companion to the single-lined spectroscopic binary HD 8375 AB. Initially noticed as an 53 m/s/yr Doppler acceleration by Bowler et al. 2010, we have obtained high-contrast adaptive optics observations at Keck using NIRC2 that spatially resolve HD 8375 C from its host(s). Astrometric measurements demonstrate that the companion shares a common proper-motion. We detect orbital motion in a clockwise direction. Multiband relative photometry measurements are consistent with a spectral-type of M1V. Our combined Doppler and imaging observations place a lower-limit of m>0.297Msun on its dynamical mass. We also provide a refined orbit for the inner pair using recent RV measurements obtained with HIRES. HD 8375 is one of many triple-star systems that are apparently missing in the solar neighborhood.

astro-ph.EP↗

arXiv2011

The Exoplanet Orbit Database

We present a database of well determined orbital parameters of exoplanets. This database comprises spectroscopic orbital elements measured for 427 planets orbiting 363 stars from radial velocity and transit measurements as reported in the literature. We have also compiled fundamental transit parameters, stellar parameters, and the method used for the planets discovery. This Exoplanet Orbit Database includes all planets with robust, well measured orbital parameters reported in peer-reviewed articles. The database is available in a searchable, filterable, and sortable form on the Web at http://exoplanets.org through the Exoplanets Data Explorer Table, and the data can be plotted and explored through the Exoplanets Data Explorer Plotter. We use the Data Explorer to generate publication-ready plots giving three examples of the signatures of exoplanet migration and dynamical evolution: We illustrate the character of the apparent correlation between mass and period in exoplanet orbits, the selection different biases between radial velocity and transit surveys, and that the multiplanet systems show a distinct semi-major axis distribution from apparently singleton systems.

astro-ph.SR↗