arXiv subjects

Yukun Huang

Publications and source records attributed to Yukun Huang.

54 records · Page 3Linked to original sources

arXiv2024

DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

Utilizing pre-trained 2D large-scale generative models, recent works are capable of generating high-quality novel views from a single in-the-wild image. However, due to the lack of information from multiple views, these works encounter difficulties in generating controllable novel views. In this paper, we present DreamComposer, a flexible and scalable framework that can enhance existing view-aware diffusion models by injecting multi-view conditions. Specifically, DreamComposer first uses a view-aware 3D lifting module to obtain 3D representations of an object from multiple views. Then, it renders the latent features of the target view from 3D representations with the multi-view feature fusion module. Finally the target view features extracted from multi-view inputs are injected into a pre-trained diffusion model. Experiments show that DreamComposer is compatible with state-of-the-art diffusion models for zero-shot novel view synthesis, further enhancing them to generate high-fidelity novel view images with multi-view conditions, ready for controllable 3D object reconstruction and various other applications.

cs.CV↗

arXiv2024

Primordial Orbital Alignment of Sednoids

We examined the past history of the three most detached TransNeptunian Objects (TNOs) -- Sedna, 2012 VP113, and Leleakuhonua (2015 TG387) -- the three clearest members of the dynamical class known as sednoids, with high perihelia distances $q$. By integrating backward their nominal (and a set of cloned) orbits for the Solar System's age, we surprisingly find that the only time all their apsidal lines tightly cluster was 4.5 Gyr ago, at perihelion longitude $\varpi$ of $200^\circ$. This "primordial alignment" is independent of the observational biases that contribute to the current on-sky clustering in the large-semimajor axis Kuiper Belt. If future sednoid discoveries confirm these findings, this strongly argues for an initial event during the planet formation epoch which imprinted this particular apsidal orientation on the early detached TNO population. Their apsidal orientations were then subsequently modified only by the simple precession from the 4 giant planets (and weakly by the galactic tide). If other sednoids also cluster around the same primordial value, various models suggesting a still present planet in the outer Solar System would be incompatible with this alignment. We inspected two scenarios that could potentially explain the primordial alignment. First, a rogue planet model (where another massive planet raises perihelia near its own longitude until ejection) naturally produces this signature. Alternatively, a close stellar passage early in Solar System history raises perihelia, but it is poor at creating strong apsidal clustering. We show that all other known $35<q<55$ au TNOs are either too perturbed or orbits are still too uncertain to provide evidence for or against this paradigm.

astro-ph.EP↗

arXiv2023

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

We present DreamWaltz, a novel framework for generating and animating complex 3D avatars given text guidance and parametric human body prior. While recent methods have shown encouraging results for text-to-3D generation of common objects, creating high-quality and animatable 3D avatars remains challenging. To create high-quality 3D avatars, DreamWaltz proposes 3D-consistent occlusion-aware Score Distillation Sampling (SDS) to optimize implicit neural representations with canonical poses. It provides view-aligned supervision via 3D-aware skeleton conditioning which enables complex avatar generation without artifacts and multiple faces. For animation, our method learns an animatable 3D avatar representation from abundant image priors of diffusion model conditioned on various poses, which could animate complex non-rigged avatars given arbitrary poses without retraining. Extensive evaluations demonstrate that DreamWaltz is an effective and robust approach for creating 3D avatars that can take on complex shapes and appearances as well as novel poses for animation. The proposed framework further enables the creation of complex scenes with diverse compositions, including avatar-avatar, avatar-object and avatar-scene interactions. See https://dreamwaltz3d.github.io/ for more vivid 3D avatar and animation results.

cs.CV↗

arXiv2023

TOSS:High-quality Text-guided Novel View Synthesis from a Single Image

In this paper, we present TOSS, which introduces text to the task of novel view synthesis (NVS) from just a single RGB image. While Zero-1-to-3 has demonstrated impressive zero-shot open-set NVS capability, it treats NVS as a pure image-to-image translation problem. This approach suffers from the challengingly under-constrained nature of single-view NVS: the process lacks means of explicit user control and often results in implausible NVS generations. To address this limitation, TOSS uses text as high-level semantic information to constrain the NVS solution space. TOSS fine-tunes text-to-image Stable Diffusion pre-trained on large-scale text-image pairs and introduces modules specifically tailored to image and camera pose conditioning, as well as dedicated training for pose correctness and preservation of fine details. Comprehensive experiments are conducted with results showing that our proposed TOSS outperforms Zero-1-to-3 with more plausible, controllable and multiview-consistent NVS results. We further support these results with comprehensive ablations that underscore the effectiveness and potential of the introduced semantic guidance and architecture design.

cs.CV↗

arXiv2023

OSSOS. XXIX. The Population and Perihelion Distribution of the Detached Kuiper Belt

The detached transneptunian objects (TNOs) are those with semimajor axes beyond the 2:1 resonance with Neptune, which are neither resonant nor scattering. Using the detached sample from the OSSOS telescopic survey, we produce the first studies of their orbital distribution based on matching the orbits and numbers of the known TNOs after accounting for survey biases. We show that the detached TNO perihelion ($q$) distribution cannot be uniform, but is instead better matched by two uniform components with a break near $q\approx40$ au. We produce parametric two-component models that are not rejectable by the OSSOS data set, and estimate that there are $36,\!000^{+12,000}_{-9,000}$ detached TNOs with absolute magnitudes $H_r < 8.66$ ($D \gtrsim 100$ km) and semimajor axes $48 < a < 250$ au (95% confidence limits). Although we believe these heuristic two-parameter models yield a correct population estimate, we then use the same methods to show that the perihelion distribution of a detached disk created by a simulated rogue planet matches the $q$ distribution even better, suggesting that the temporary presence of other planets in the early Solar System is a promising model to create today's large semimajor axis TNO population. This numerical model results in a detached TNO population estimate of $48,\!000^{+15,000}_{-12,000}$. Because this illustrates how difficult-to-detect $q>50$ au objects are likely present, we conclude that there are $(5 \pm 2)\times10^4$ dynamically detached TNOs, which are thus roughly twice as numerous as the entire transneptunian hot main belt.

astro-ph.EP↗

arXiv2022

In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models

Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine in-context learning objectives with language modeling objectives to distill both the ability to read in-context examples and task knowledge to the smaller models. We perform in-context learning distillation under two different few-shot learning paradigms: Meta In-context Tuning (Meta-ICT) and Multitask In-context Tuning (Multitask-ICT). Multitask-ICT performs better on multitask few-shot learning but also requires more computation than Meta-ICT. Our method shows consistent improvements for both Meta-ICT and Multitask-ICT on two benchmarks: LAMA and CrossFit. Our extensive experiments and analysis reveal that in-context learning objectives and language modeling objectives are complementary under the Multitask-ICT paradigm. In-context learning objectives achieve the best performance when combined with language modeling objectives.

cs.CL↗

arXiv2022

Neural Dependencies Emerging from Learning Massive Categories

This work presents two astonishing findings on neural networks learned for large-scale image classification. 1) Given a well-trained model, the logits predicted for some category can be directly obtained by linearly combining the predictions of a few other categories, which we call \textbf{neural dependency}. 2) Neural dependencies exist not only within a single model, but even between two independently learned models, regardless of their architectures. Towards a theoretical analysis of such phenomena, we demonstrate that identifying neural dependencies is equivalent to solving the Covariance Lasso (CovLasso) regression problem proposed in this paper. Through investigating the properties of the problem solution, we confirm that neural dependency is guaranteed by a redundant logit covariance matrix, which condition is easily met given massive categories, and that neural dependency is highly sparse, implying that one category correlates to only a few others. We further empirically show the potential of neural dependencies in understanding internal data correlations, generalizing models to unseen categories, and improving model robustness with a dependency-derived regularizer. Code for this work will be made publicly available.

cs.LG↗

arXiv2022

A Rogue Planet Helps Populate the Distant Kuiper Belt

The orbital distribution of transneptunian objects (TNOs) in the distant Kuiper Belt (with semimajor axes beyond the 2:1 resonance, roughly $a$=50-100 au) provides constraints on the dynamical history of the outer solar system. Recent studies show two striking features of this region: 1) a very large population of objects in distant mean-motion resonances with Neptune, and 2) the existence of a substantial detached population (non-resonant objects largely decoupled from Neptune). Neptune migration models are able to implant some resonant and detached objects during the planet migration era, but many fail to match a variety of aspects of the orbital distribution. In this work, we report simulations carried out using an improved version of the GPU-based code GLISSE, following 100,000 test particles per simulation in parallel while handling their planetary close encounters. We demonstrate for the first time that a 2 Earth-mass rogue planet temporarily present during planet formation can abundantly populate both the distant resonances and the detached populations, surprisingly even without planetary migration. We show how weak encounters with the rogue greatly increase the efficiency of filling the resonances, while also dislodging TNOs out of resonance once they reach high perihelia. The rogue's secular gravitational influence simultaneously generates numerous detached objects observed at all semimajor axes. These results suggest that the early presence of additional planet(s) reproduces the observed TNO orbital structure in the distant Kuiper Belt.

astro-ph.EP↗

arXiv2022

Whole-Body Lesion Segmentation in 18F-FDG PET/CT

There has been growing research interest in using deep learning based method to achieve fully automated segmentation of lesion in Positron emission tomography computed tomography(PET CT) scans for the prognosis of various cancers. Recent advances in the medical image segmentation shows the nnUNET is feasible for diverse tasks. However, lesion segmentation in the PET images is not straightforward, because lesion and physiological uptake has similar distribution patterns. The Distinction of them requires extra structural information in the CT images. The present paper introduces a nnUNet based method for the lesion segmentation task. The proposed model is designed on the basis of the joint 2D and 3D nnUNET architecture to predict lesions across the whole body. It allows for automated segmentation of potential lesions. We evaluate the proposed method in the context of AutoPet Challenge, which measures the lesion segmentation performance in the metrics of dice score, false-positive volume and false-negative volume.

eess.IV↗

arXiv2022

Rank Diminishing in Deep Neural Networks

The rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. In particular, the assumption of low-rank feature representations leads to algorithmic developments in many architectures. For neural networks, however, the intrinsic mechanism that yields low-rank structures remains vague and unclear. To fill this gap, we perform a rigorous study on the behavior of network rank, focusing particularly on the notion of rank deficiency. We theoretically establish a universal monotonic decreasing property of network rank from the basic rules of differential and algebraic composition, and uncover rank deficiency of network blocks and deep function coupling. By virtue of our numerical tools, we provide the first empirical analysis of the per-layer behavior of network rank in practical settings, i.e., ResNets, deep MLPs, and Transformers on ImageNet. These empirical results are in direct accord with our theory. Furthermore, we reveal a novel phenomenon of independence deficit caused by the rank deficiency of deep networks, where classification confidence of a given category can be linearly decided by the confidence of a handful of other categories. The theoretical results of this work, together with the empirical findings, may advance understanding of the inherent principles of deep neural networks.

cs.LG↗

arXiv2022

Learning a Better Initialization for Soft Prompts via Meta-Learning

Prompt tuning (PT) is an effective approach to adapting pre-trained language models to downstream tasks. Without a good initialization, prompt tuning doesn't perform well under few-shot settings. So pre-trained prompt tuning (PPT) is proposed to initialize prompts by leveraging pre-training data. We propose MetaPT (Meta-learned Prompt Tuning) to further improve PPT's initialization by considering latent structure within the pre-training data. Specifically, we introduce the structure by first clustering pre-training data into different auxiliary tasks with unsupervised methods. Then we use these tasks to pre-train prompts with a meta-learning algorithm. Such a process can make prompts learn a better initialization by discovering commonalities among these auxiliary tasks. We evaluate our method on seven downstream tasks. Our MetaPT achieves better and more stable performance than the state-of-the-art method.

cs.CL↗

arXiv2022

Free Inclinations for Transneptunian Objects in the Main Kuiper Belt

There is a complex inclination structure present in the transneptunian object (TNO) orbital distribution in the main classical belt region (between orbital semimajor axes of 39 and 48 au). The long-term gravitational effects of the giant planets make TNO orbits precess, but non-resonant objects maintain a nearly constant 'free' inclination ($I_\text{free}$) with respect to a local forced precession pole. Because of the likely cosmogonic importance of the distribution of this quantity, we tabulate free inclinations for all main-belt TNOs, each individually computed using barycentric orbital elements with respect to each object's local forcing pole. We show that the simplest method, based on the Laplace-Lagrange secular theory, is unable to give correct forcing poles for objects near the $ν_{18}$ secular resonance, resulting in poorly conserved $I_\text{free}$ values in much of the main belt. We thus instead implemented an averaged Hamiltonian to obtain the expected nodal precession for each TNO, yielding significantly more accurate free inclinations for non-resonant objects. For the vast majority (96\%) of classical belt TNOs, these $I_\text{free}$ values are conserved to $<1^\circ$ over 4 Gyr numerical simulations, demonstrating the advantage of using this well-conserved quantity in studies of the TNO population and its primordial inclination profile; our computed distributions only reinforce the idea of a very co-planar surviving 'cold' primordial population, overlain by a large $I$-width implanted 'hot' population.

astro-ph.EP↗

arXiv2020

Four Billion Year Stability of the Earth-Mars Belt

Previous work has demonstrated orbital stability for 100 Myr of initially near-circular and coplanar small bodies in a region termed the 'Earth-Mars belt' from 1.08 au $< a <$ 1.28 au. Via numerical integration of 3000 particles, we studied orbits from 1.04-1.30 au for the age of the Solar system. We show that on this time scale, except for a few locations where mean-motion resonances with Earth affect stability, only a narrower `Earth-Mars belt' covering $a\sim(1.09, 1.17)$ au, $e<0.04$, and $I<1^\circ$ has over half of the initial orbits survive for 4.5 Gyr. In addition to mean-motion resonances, we are able to see how the $ν_3$, $ν_4$, and $ν_6$ secular resonances contribute to long-term instability in the outer (1.17-1.30 au) region on Gyr time scales. We show that all of the (rather small) near-Earth objects (NEOs) in or close to the Earth-Mars belt appear to be consistent with recently arrived transient objects by comparing to a NEO steady-state model. Given the $<200$ m scale of these NEOs, we estimated the Yarkovsky drift rates in semimajor axis, and use these to estimate that primordial asteroids with a diameter of 100 km or larger in the Earth-Mars belt would likely survive. We conclude that only a few 100-km sized asteroids could have been present in the belt's region at the end of the terrestrial planet formation.

astro-ph.EP↗

arXiv2020

Real-world Person Re-Identification via Degradation Invariance Learning

Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e.g., low-resolution, weak illumination, blurring and adverse weather. On the one hand, these degradations lead to severe discriminative information loss, which significantly obstructs identity representation learning; on the other hand, the feature mismatch problem caused by low-level visual variations greatly reduces retrieval performance. An intuitive solution to this problem is to utilize low-level image restoration methods to improve the image quality. However, existing restoration methods cannot directly serve to real-world Re-ID due to various limitations, e.g., the requirements of reference samples, domain gap between synthesis and reality, and incompatibility between low-level and high-level methods. In this paper, to solve the above problem, we propose a degradation invariance learning framework for real-world person Re-ID. By introducing a self-supervised disentangled representation learning strategy, our method is able to simultaneously extract identity-related robust features and remove real-world degradations without extra supervision. We use low-resolution images as the main demonstration, and experiments show that our approach is able to achieve state-of-the-art performance on several Re-ID benchmarks. In addition, our framework can be easily extended to other real-world degradation factors, such as weak illumination, with only a few modifications.

cs.CV↗

arXiv2019

On the Instability of Saturn's Hypothetical Retrograde Co-orbitals

We find an interesting fact that fictitious retrograde co-orbitals of Saturn, or small bodies inside the retrograde 1:1 resonance with Saturn, are highly unstable in our numerical simulations. It is shown that in the presence of Jupiter, the retrograde co-orbitals will get ejected from Saturn's co-orbital space within a timescale of 10 Myr. This scenario reminds us of the instability of Saturn Trojans caused by both the Great Inequality and the secular resonances. Therefore, we carry out in-depth inspections on both mechanisms and prove that the retrograde resonance overlap, raised by Great Inequality, cannot serve as an explanation for the instability of retrograde co-orbitals, due to the weakness of the retrograde 2:5 resonance with Jupiter at a low eccentricity. However, we discover that both $ν_5$ and $ν_6$ secular resonances contribute to the slow growth of the eccentricity, therefore, are possibly the primary causes of the instability inside Saturn's retrograde co-orbital space.

astro-ph.EP↗

arXiv2018

Kozai-Lidov Mechanism inside Retrograde Mean Motion Resonances

As the discoveries of more minor bodies in retrograde resonances with giant planets, such as 2015 BZ509 and 2006 RJ2, our curiosity about the Kozai-Lidov dynamics inside the retrograde resonance has been sparked. In this study, we focus on the 3D retrograde resonance problem and investigate how the resonant dynamics of a minor body impacts on its own Kozai-Lidov cycle. Firstly we deduce the action-angle variables and canonical transformations that deal with the retrograde orbit specifically. After obtaining the dominant Hamiltonian of this problem, we then carry out the numerical averaging process in closed form to generate phase-space portraits on a $e-ω$ space. The retrograde 1:1 resonance is particularly scrutinized in detail, and numerical results from a CRTBP model shows a great agreement with the our semi-analytical portraits. On this basis, we inspect two real minor bodies currently trapped in retrograde 1:1 mean motion resonance. It is shown that they have different Kozai-Lidov states, which can be used to analyze the stability of their unique resonances. In the end, we further inspect the Kozai-Lidov dynamics inside the 2:1 and 2:5 retrograde resonance, and find distinct dynamical bifurcations of equilibrium points on phase-space portraits.

astro-ph.EP↗

arXiv2018

Centaurs potentially in retrograde co-orbit resonance with Saturn

Aims. 2015 BZ509 is the first asteroid confirmed to be in retrograde co-orbit resonance (or 1/-1 resonance) with the giant planets in the solar system. While Saturn is the only giant planet whose Trojans are not discovered until now, we identify some small bodies among Centaurs and Damocloids that are potentially in 1/-1 resonance with Saturn in the present study. Methods. We integrate numerically the motion of the 1000 clones (include the nominal orbit) of each Centaur whose orbit has a semi-major axis between 9.3 au and 9.8 au and an inclination i > 90 deg. To confirm and evaluate the 1/-1 resonant configurations mentioned above, we introduce a useful one-degree integrable approximation for planar 1/-1 resonance. Results. We identify four candidates potentially in 1/-1 resonance with Saturn. The capture in this particular resonant state during the 40000 yr integration timespan is very common for 2006 RJ2 (906/1000 clones), 2006 BZ8 (878/1000 clones), and 2017 SV13 (998/1000 clones), and it is less likely for 2012 YE8 (426/1000 clones). According to our statistical results, 2006 RJ2 is the best candidate to be currently in a 1/-1 mean motion resonance with Saturn, and 2017 SV13 is another important potential candidate. Moreover, 2012 YE8 and 2006 BZ8 are also Centaurs of interest but their current and long-term 1/-1 resonant state with Saturn is less likely. The proportions of the clones captured in the relative long-term stable co-orbit resonance (over 10000 yr) are also given. Conclusions. Small bodies in retrograde co-orbit resonance with giant planets may be more common than previously expected. Identification of these potential mysterious minor bodies encourages the search for such objects on a larger scale in our solar system. The findings of this paper are also useful for understanding the origin and dynamical evolution of the Centaurs and Damocloids on retrograde orbits.

astro-ph.EP↗

arXiv2018

Dynamic portrait of the retrograde 1:1 mean motion resonance

Asteroids in mean motion resonances with giant planets are common in the solar system, but it was not until recently that several asteroids in retrograde mean motion resonances with Jupiter and Saturn were discovered. A retrograde co-orbital asteroid of Jupiter, 2015 BZ509 is confirmed to be in a long-term stable retrograde 1:1 mean motion resonance with Jupiter, which gives rise to our interests in its unique resonant dynamics. In this paper, we investigate the phase-space structure of the retrograde 1:1 resonance in detail within the framework of the circular restricted three-body problem. We construct a simple integrable approximation for the planar retrograde resonance using canonical contact transformation and numerically employ the averaging procedure in closed form. The phase portrait of the retrograde 1:1 resonance is depicted with the level curves of the averaged Hamiltonian. We thoroughly analyze all possible librations in the co-orbital region and uncover a new apocentric libration for the retrograde 1:1 resonance inside the planet's orbit. We also observe the significant jumps in orbital elements for outer and inner apocentric librations, which are caused by close encounters with the perturber.

astro-ph.EP↗