Search

A combined experimental and theoretical study is carried out on the three-body recombination process in a gas of microwave-shielded polar molecules. For ground-state polar molecules dressed with a strong microwave field, field-linked bound states can appear in the intermolecular potential. We model three-body recombination into such bound states using classical trajectory calculations. Our results show that recombination can explain the enhanced loss rates observed at small microwave detunings in trapped samples of bosonic NaCs [Bigagli, $\textit{et al.}$, Nat. Phys. $\textbf{19}$ 1579-1584 (2023)]. Specifically, our calculations reproduce the experimentally measured three-body loss rates across a wide range of microwave Rabi couplings, detunings, and temperatures. This work suggests that for bosonic shielded molecular systems in which the two-body loss is sufficiently suppressed and a field-linked bound state is present, the dominant loss process will be three-body recombination., Comment: 11 pages, 5 figures

We report on the optical polarizability of microwave-shielded ultracold NaCs molecules in an optical dipole trap. While dressing a pair of rotational states with a microwave field, we observe a marked dependence of the optical polarizability on the intensity and detuning of the dressing field. To precisely characterize differential energy shifts between dressed rotational states, we establish dressed-state spectroscopy. For strong dressing fields, we find that a magic rotational transition can be engineered and demonstrate its insensitivity to laser intensity fluctuations. The results of this work have direct relevance for evaporative cooling and the recent demonstration of molecular Bose-Einstein condensates [Bigagli, et al., Nature (2024)] and may open a door to precision microwave spectroscopy in interacting many-body systems of microwave-shielded molecules., Comment: 5 pages, 4 figures

Temporal Graph Networks (TGNs) have demonstrated their remarkable performance in modeling temporal interaction graphs. These works can generate temporal node representations by encoding the surrounding neighborhoods for the target node. However, an inherent limitation of existing TGNs is their reliance on fixed, hand-crafted rules for neighborhood encoding, overlooking the necessity for an adaptive and learnable neighborhood that can accommodate both personalization and temporal evolution across different timestamps. In this paper, we aim to enhance existing TGNs by introducing an adaptive neighborhood encoding mechanism. We present SEAN, a flexible plug-and-play model that can be seamlessly integrated with existing TGNs, effectively boosting their performance. To achieve this, we decompose the adaptive neighborhood encoding process into two phases: (i) representative neighbor selection, and (ii) temporal-aware neighborhood information aggregation. Specifically, we propose the Representative Neighbor Selector component, which automatically pinpoints the most important neighbors for the target node. It offers a tailored understanding of each node's unique surrounding context, facilitating personalization. Subsequently, we propose a Temporal-aware Aggregator, which synthesizes neighborhood aggregation by selectively determining the utilization of aggregation routes and decaying the outdated information, allowing our model to adaptively leverage both the contextually significant and current information during aggregation. We conduct extensive experiments by integrating SEAN into three representative TGNs, evaluating their performance on four public datasets and one financial benchmark dataset introduced in this paper. The results demonstrate that SEAN consistently leads to performance improvements across all models, achieving SOTA performance and exceptional robustness., Comment: KDD'2024 Research Track Paper

Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems. To facilitate representation learning on TIGs, researchers have proposed a series of TIG models. However, these models are still facing two tough gaps between the pre-training and downstream predictions in their ``pre-train, predict'' training paradigm. First, the temporal discrepancy between the pre-training and inference data severely undermines the models' applicability in distant future predictions on the dynamically evolving data. Second, the semantic divergence between pretext and downstream tasks hinders their practical applications, as they struggle to align with their learning and prediction capabilities across application scenarios. Recently, the ``pre-train, prompt'' paradigm has emerged as a lightweight mechanism for model generalization. Applying this paradigm is a potential solution to solve the aforementioned challenges. However, the adaptation of this paradigm to TIGs is not straightforward. The application of prompting in static graph contexts falls short in temporal settings due to a lack of consideration for time-sensitive dynamics and a deficiency in expressive power. To address this issue, we introduce Temporal Interaction Graph Prompting (TIGPrompt), a versatile framework that seamlessly integrates with TIG models, bridging both the temporal and semantic gaps. In detail, we propose a temporal prompt generator to offer temporally-aware prompts for different tasks. These prompts stand out for their minimalistic design, relying solely on the tuning of the prompt generator with very little supervision data. To cater to varying computational resource demands, we propose an extended ``pre-train, prompt-based fine-tune'' paradigm, offering greater flexibility. Through extensive experiments, the TIGPrompt demonstrates the SOTA performance and remarkable efficiency advantages., Comment: 11 pages, 8 figures

Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered third-person-view vision models, but its application to embodied egocentric perception tasks remains largely unexplored. A critical challenge lies in simulating natural human movements and behaviors that effectively steer the embodied cameras to capture a faithful egocentric representation of the 3D world. To address this challenge, we introduce EgoGen, a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. Combined with collision-avoiding motion primitives and a two-stage reinforcement learning approach, our motion synthesis model offers a closed-loop solution where the embodied perception and movement of the virtual human are seamlessly coupled. Compared to previous works, our model eliminates the need for a pre-defined global path, and is directly applicable to dynamic environments. Combined with our easy-to-use and scalable data generation pipeline, we demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views. EgoGen will be fully open-sourced, offering a practical solution for creating realistic egocentric training data and aiming to serve as a useful tool for egocentric computer vision research. Refer to our project page: https://ego-gen.github.io/., Comment: Accepted by CVPR 2024 (Oral). 23 pages, 17 figures. Project page: https://ego-gen.github.io/

We propose RoHM, an approach for robust 3D human motion reconstruction from monocular RGB(-D) videos in the presence of noise and occlusions. Most previous approaches either train neural networks to directly regress motion in 3D or learn data-driven motion priors and combine them with optimization at test time. The former do not recover globally coherent motion and fail under occlusions; the latter are time-consuming, prone to local minima, and require manual tuning. To overcome these shortcomings, we exploit the iterative, denoising nature of diffusion models. RoHM is a novel diffusion-based motion model that, conditioned on noisy and occluded input data, reconstructs complete, plausible motions in consistent global coordinates. Given the complexity of the problem -- requiring one to address different tasks (denoising and infilling) in different solution spaces (local and global motion) -- we decompose it into two sub-tasks and learn two models, one for global trajectory and one for local motion. To capture the correlations between the two, we then introduce a novel conditioning module, combining it with an iterative inference scheme. We apply RoHM to a variety of tasks -- from motion reconstruction and denoising to spatial and temporal infilling. Extensive experiments on three popular datasets show that our method outperforms state-of-the-art approaches qualitatively and quantitatively, while being faster at test time. The code is available at https://sanweiliti.github.io/ROHM/ROHM.html., Comment: With the appendix included

Ensembles of particles governed by quantum mechanical laws exhibit fascinating emergent behavior. Atomic quantum gases, liquid helium, and electrons in quantum materials all show distinct properties due to their composition and interactions. Quantum degenerate samples of bosonic dipolar molecules promise the realization of novel phases of matter with tunable dipolar interactions and new avenues for quantum simulation and quantum computation. However, rapid losses, even when reduced through collisional shielding techniques, have so far prevented cooling to a Bose-Einstein condensate (BEC). In this work, we report on the realization of a BEC of dipolar molecules. By strongly suppressing two- and three-body losses via enhanced collisional shielding, we evaporatively cool sodium-cesium (NaCs) molecules to quantum degeneracy. The BEC reveals itself via a bimodal distribution and a phase-space-density exceeding one. BECs with a condensate fraction of 60(10) % and a temperature of 6(2) nK are created and found to be stable with a lifetime close to 2 seconds. This work opens the door to the exploration of dipolar quantum matter in regimes that have been inaccessible so far, promising the creation of exotic dipolar droplets, self-organized crystal phases, and dipolar spin liquids in optical lattices., Comment: 10 pages, 7 figures

A swarm of robots has advantages over a single robot, since it can explore larger areas much faster and is more robust to single-point failures. Accurate relative positioning is necessary to successfully carry out a collaborative mission without collisions. When Visual Simultaneous Localization and Mapping (VSLAM) is used to estimate the poses of each robot, inter-agent loop closing is widely applied to reduce the relative positioning errors. This technique can mitigate errors using the feature points commonly observed by different robots. However, it requires significant computing and communication capabilities to detect inter-agent loops, and to process the data transmitted by multiple agents. In this paper, we propose Collaborative SLAM using Visual Odometry and Range measurements (CoVOR-SLAM) to overcome this challenge. In the framework of CoVOR-SLAM, robots only need to exchange pose estimates, covariances (uncertainty) of the estimates, and range measurements between robots. Since CoVOR-SLAM does not require to associate visual features and map points observed by different agents, the computational and communication loads are significantly reduced. The required range measurements can be obtained using pilot signals of the communication system, without requiring complex additional infrastructure. We tested CoVOR-SLAM using real images as well as real ultra-wideband-based ranges obtained with two rovers. In addition, CoVOR-SLAM is evaluated with a larger scale multi-agent setup exploiting public image datasets and ranges generated using a realistic simulation. The results show that CoVOR-SLAM can accurately estimate the robots' poses, requiring much less computational power and communication capabilities than the inter-agent loop closing technique., Comment: Submitted to the IEEE Transactions on Intelligent Transportation Systems

Temporal Graph Networks (TGNs) have shown remarkable performance in learning representation for continuous-time dynamic graphs. However, real-world dynamic graphs typically contain diverse and intricate noise. Noise can significantly degrade the quality of representation generation, impeding the effectiveness of TGNs in downstream tasks. Though structure learning is widely applied to mitigate noise in static graphs, its adaptation to dynamic graph settings poses two significant challenges. i) Noise dynamics. Existing structure learning methods are ill-equipped to address the temporal aspect of noise, hampering their effectiveness in such dynamic and ever-changing noise patterns. ii) More severe noise. Noise may be introduced along with multiple interactions between two nodes, leading to the re-pollution of these nodes and consequently causing more severe noise compared to static graphs. In this paper, we present RDGSL, a representation learning method in continuous-time dynamic graphs. Meanwhile, we propose dynamic graph structure learning, a novel supervisory signal that empowers RDGSL with the ability to effectively combat noise in dynamic graphs. To address the noise dynamics issue, we introduce the Dynamic Graph Filter, where we innovatively propose a dynamic noise function that dynamically captures both current and historical noise, enabling us to assess the temporal aspect of noise and generate a denoised graph. We further propose the Temporal Embedding Learner to tackle the challenge of more severe noise, which utilizes an attention mechanism to selectively turn a blind eye to noisy edges and hence focus on normal edges, enhancing the expressiveness for representation generation that remains resilient to noise. Our method demonstrates robustness towards downstream tasks, resulting in up to 5.1% absolute AUC improvement in evolving classification versus the second-best baseline.

Continuous-time dynamic graph modeling is a crucial task for many real-world applications, such as financial risk management and fraud detection. Though existing dynamic graph modeling methods have achieved satisfactory results, they still suffer from three key limitations, hindering their scalability and further applicability. i) Indiscriminate updating. For incoming edges, existing methods would indiscriminately deal with them, which may lead to more time consumption and unexpected noisy information. ii) Ineffective node-wise long-term modeling. They heavily rely on recurrent neural networks (RNNs) as a backbone, which has been demonstrated to be incapable of fully capturing node-wise long-term dependencies in event sequences. iii) Neglect of re-occurrence patterns. Dynamic graphs involve the repeated occurrence of neighbors that indicates their importance, which is disappointedly neglected by existing methods. In this paper, we present iLoRE, a novel dynamic graph modeling method with instant node-wise Long-term modeling and Re-occurrence preservation. To overcome the indiscriminate updating issue, we introduce the Adaptive Short-term Updater module that will automatically discard the useless or noisy edges, ensuring iLoRE's effectiveness and instant ability. We further propose the Long-term Updater to realize more effective node-wise long-term modeling, where we innovatively propose the Identity Attention mechanism to empower a Transformer-based updater, bypassing the limited effectiveness of typical RNN-dominated designs. Finally, the crucial re-occurrence patterns are also encoded into a graph module for informative representation learning, which will further improve the expressiveness of our method. Our experimental results on real-world datasets demonstrate the effectiveness of our iLoRE for dynamic graph modeling.

Temporal Interaction Graphs (TIGs) are widely employed to model intricate real-world systems such as financial systems and social networks. To capture the dynamism and interdependencies of nodes, existing TIG embedding models need to process edges sequentially and chronologically. However, this requirement prevents it from being processed in parallel and struggle to accommodate burgeoning data volumes to GPU. Consequently, many large-scale temporal interaction graphs are confined to CPU processing. Furthermore, a generalized GPU scaling and acceleration approach remains unavailable. To facilitate large-scale TIGs' implementation on GPUs for acceleration, we introduce a novel training approach namely Streaming Edge Partitioning and Parallel Acceleration for Temporal Interaction Graph Embedding (SPEED). The SPEED is comprised of a Streaming Edge Partitioning Component (SEP) which addresses space overhead issue by assigning fewer nodes to each GPU, and a Parallel Acceleration Component (PAC) which enables simultaneous training of different sub-graphs, addressing time overhead issue. Our method can achieve a good balance in computing resources, computing time, and downstream task performance. Empirical validation across 7 real-world datasets demonstrates the potential to expedite training speeds by a factor of up to 19.29x. Simultaneously, resource consumption of a single-GPU can be diminished by up to 69%, thus enabling the multiple GPU-based training and acceleration encompassing millions of nodes and billions of edges. Furthermore, our approach also maintains its competitiveness in downstream tasks., Comment: 13 pages, 8 figures

The surgical usage of Mixed Reality (MR) has received growing attention in areas such as surgical navigation systems, skill assessment, and robot-assisted surgeries. For such applications, pose estimation for hand and surgical instruments from an egocentric perspective is a fundamental task and has been studied extensively in the computer vision field in recent years. However, the development of this field has been impeded by a lack of datasets, especially in the surgical field, where bloody gloves and reflective metallic tools make it hard to obtain 3D pose annotations for hands and objects using conventional methods. To address this issue, we propose POV-Surgery, a large-scale, synthetic, egocentric dataset focusing on pose estimation for hands with different surgical gloves and three orthopedic surgical instruments, namely scalpel, friem, and diskplacer. Our dataset consists of 53 sequences and 88,329 frames, featuring high-resolution RGB-D video streams with activity annotations, accurate 3D and 2D annotations for hand-object pose, and 2D hand-object segmentation masks. We fine-tune the current SOTA methods on POV-Surgery and further show the generalizability when applying to real-life cases with surgical gloves and tools by extensive evaluations. The code and the dataset are publicly available at batfacewayne.github.io/POV_Surgery_io/.

We report on the design and characterization of a compact microwave antenna for atomic and molecular physics experiments. The antenna is comprised of four loop antennas arranged in cloverleaf shape, allowing for precise adjustment of polarization by tuning the relative phase of the loops. We optimize the antenna for left-circularly polarized microwaves at 3.5 GHz and characterize its performance using ultracold NaCs molecules as a precise quantum sensor. Observing an unusually high Rabi frequency of $2\pi \times 46$ MHz, we extract an electric field amplitude of 33(2) V/cm at 22 mm distance from the antenna. The polarization ellipticity is 2.3(4) degrees, corresponding to a 24 dB suppression of right-circular polarization. The cloverleaf antenna is planar and provides large optical access, making it highly suitable for quantum control of atoms and molecules, and potentially other quantum systems that operate in the microwave regime., Comment: 6 pages, 3 figures

Automatic perception of human behaviors during social interactions is crucial for AR/VR applications, and an essential component is estimation of plausible 3D human pose and shape of our social partners from the egocentric view. One of the biggest challenges of this task is severe body truncation due to close social distances in egocentric scenarios, which brings large pose ambiguities for unseen body parts. To tackle this challenge, we propose a novel scene-conditioned diffusion method to model the body pose distribution. Conditioned on the 3D scene geometry, the diffusion model generates bodies in plausible human-scene interactions, with the sampling guided by a physics-based collision score to further resolve human-scene inter-penetrations. The classifier-free training enables flexible sampling with different conditions and enhanced diversity. A visibility-aware graph convolution model guided by per-joint visibility serves as the diffusion denoiser to incorporate inter-joint dependencies and per-body-part control. Extensive evaluations show that our method generates bodies in plausible interactions with 3D scenes, achieving both superior accuracy for visible joints and diversity for invisible body parts. The code is available at https://sanweiliti.github.io/egohmr/egohmr.html., Comment: Camera ready version for ICCV 2023, appendix included

Stable ultracold ensembles of dipolar molecules hold great promise for many-body quantum physics, but high inelastic loss rates have been a long-standing challenge. Recently, it was shown that gases of fermionic molecules can be effectively stabilized through external fields. However, many quantum applications will benefit from molecular ensembles with bosonic statistics. Here, we stabilize a bosonic gas of strongly dipolar NaCs molecules against inelastic losses via microwave shielding, decreasing losses by more than a factor of 200 and reaching lifetimes on the scale of 1 second. We also measure high elastic scattering rates, a result of strong dipolar interactions, and observe the anisotropic nature of dipolar collisions. Finally, we demonstrate evaporative cooling of a bosonic molecular gas to a temperature of 36(5) nK, increasing its phase-space density by a factor of 20. This work is a critical step towards the creation of a Bose-Einstein condensate of dipolar molecules., Comment: 14 pages, 11 figures

We present a study of two-photon pathways for the transfer of NaCs molecules to their rovibrational ground state. Starting from NaCs Feshbach molecules, we perform bound-bound excited state spectroscopy in the wavelength range from 900~nm to 940~nm, covering more than 30 vibrational states of the $c \, ^3\Sigma^+$, $b \, ^3\Pi$, and $B \, ^1\Pi$ electronic states. Analyzing the rotational substructure, we identify the highly mixed $c \, ^3\Sigma^+_1 \, |v=22 \rangle \sim b \, ^3\Pi_1 \, | v=54\rangle$ state as an efficient bridge for stimulated Raman adiabatic passage (STIRAP). We demonstrate transfer into the NaCs ground state with an efficiency of up to 88(4)\%. Highly efficient transfer is critical for the realization of many-body quantum phases of strongly dipolar NaCs molecules and high fidelity detection of single molecules, for example, in spin physics experiments in optical lattices and quantum information experiments in optical tweezer arrays., Comment: 17 pages, 8 figures

We report on the creation of bosonic NaCs molecules in their absolute rovibrational ground state via stimulated Raman adiabatic passage. We create ultracold gases with up to 22,000 dipolar NaCs molecules at a temperature of 300(50) nK and a peak density of $1.0(4) \times 10^{12}$ cm$^{-3}$. We demonstrate comprehensive quantum state control by preparing the molecules in a specific electronic, vibrational, rotational, and hyperfine state. Employing the tunability and strength of the permanent electric dipole moment of NaCs, we induce dipole moments of up to 2.6 D. Dipolar systems of NaCs molecules are uniquely suited to explore strongly interacting phases in dipolar quantum matter., Comment: 6 pages, 5 figures

We report on the creation of ultracold gases of bosonic Feshbach molecules of NaCs. The molecules are associated from overlapping gases of Na and Cs using a Feshbach resonance at 864.12(5) G. We characterize the Feshbach resonance using bound state spectroscopy, in conjunction with a coupled-channel calculation. By varying the temperature and atom numbers of the initial atomic mixtures, we demonstrate the association of NaCs gases over a wide dynamic range of molecule numbers and temperatures, reaching 70 nK for our coldest systems and a phase-space density near 0.1. This is an important stepping-stone for the creation of degenerate gases of strongly dipolar NaCs molecules in their absolute ground state., Comment: 6 pages, 5 figures, supplemental material

The synthesis of human grasping has numerous applications including AR/VR, video games and robotics. While methods have been proposed to generate realistic hand-object interaction for object grasping and manipulation, these typically only consider interacting hand alone. Our goal is to synthesize whole-body grasping motions. Starting from an arbitrary initial pose, we aim to generate diverse and natural whole-body human motions to approach and grasp a target object in 3D space. This task is challenging as it requires modeling both whole-body dynamics and dexterous finger movements. To this end, we propose SAGA (StochAstic whole-body Grasping with contAct), a framework which consists of two key components: (a) Static whole-body grasping pose generation. Specifically, we propose a multi-task generative model, to jointly learn static whole-body grasping poses and human-object contacts. (b) Grasping motion infilling. Given an initial pose and the generated whole-body grasping pose as the start and end of the motion respectively, we design a novel contact-aware generative motion infilling module to generate a diverse set of grasp-oriented motions. We demonstrate the effectiveness of our method, which is a novel generative framework to synthesize realistic and expressive whole-body motions that approach and grasp randomly placed unseen objects. Code and models are available at https://jiahaoplus.github.io/SAGA/saga.html., Comment: Accepted by ECCV 2022. Project page: https://jiahaoplus.github.io/SAGA/saga.html

Understanding social interactions from egocentric views is crucial for many applications, ranging from assistive robotics to AR/VR. Key to reasoning about interactions is to understand the body pose and motion of the interaction partner from the egocentric view. However, research in this area is severely hindered by the lack of datasets. Existing datasets are limited in terms of either size, capture/annotation modalities, ground-truth quality, or interaction diversity. We fill this gap by proposing EgoBody, a novel large-scale dataset for human pose, shape and motion estimation from egocentric views, during interactions in complex 3D scenes. We employ Microsoft HoloLens2 headsets to record rich egocentric data streams (including RGB, depth, eye gaze, head and hand tracking). To obtain accurate 3D ground truth, we calibrate the headset with a multi-Kinect rig and fit expressive SMPL-X body meshes to multi-view RGB-D frames, reconstructing 3D human shapes and poses relative to the scene, over time. We collect 125 sequences, spanning diverse interaction scenarios, and propose the first benchmark for 3D full-body pose and shape estimation of the social partner from egocentric views. We extensively evaluate state-of-the-art methods, highlight their limitations in the egocentric scenario, and address such limitations leveraging our high-quality annotations. Data and code are available at https://sanweiliti.github.io/egobody/egobody.html., Comment: Camera ready version for ECCV 2022, appendix included

Recovering high-quality 3D human motion in complex scenes from monocular videos is important for many applications, ranging from AR/VR to robotics. However, capturing realistic human-scene interactions, while dealing with occlusions and partial views, is challenging; current approaches are still far from achieving compelling results. We address this problem by proposing LEMO: LEarning human MOtion priors for 4D human body capture. By leveraging the large-scale motion capture dataset AMASS, we introduce a novel motion smoothness prior, which strongly reduces the jitters exhibited by poses recovered over a sequence. Furthermore, to handle contacts and occlusions occurring frequently in body-scene interactions, we design a contact friction term and a contact-aware motion infiller obtained via per-instance self-supervised training. To prove the effectiveness of the proposed motion priors, we combine them into a novel pipeline for 4D human body capture in 3D scenes. With our pipeline, we demonstrate high-quality 4D human body capture, reconstructing smooth motions and physically plausible body-scene interactions. The code and data are available at https://sanweiliti.github.io/LEMO/LEMO.html., Comment: Accepted by ICCV 2021, camera ready version with appendix

Human emotions can be inferred from facial expressions. However, the annotations of facial expressions are often highly noisy in common emotion coding models, including categorical and dimensional ones. To reduce human labelling effort on multi-task labels, we introduce a new problem of facial emotion recognition with noisy multi-task annotations. For this new problem, we suggest a formulation from the point of joint distribution match view, which aims at learning more reliable correlations among raw facial images and multi-task labels, resulting in the reduction of noise influence. In our formulation, we exploit a new method to enable the emotion prediction and the joint distribution learning in a unified adversarial learning game. Evaluation throughout extensive experiments studies the real setups of the suggested new problem, as well as the clear superiority of the proposed method over the state-of-the-art competing methods on either the synthetic noisy labeled CIFAR-10 or practical noisy multi-task labeled RAF and AffectNet. The code is available at https://github.com/sanweiliti/noisyFER., Comment: Accepted by 2021 WACV, camera-ready version with appendix

High fidelity digital 3D environments have been proposed in recent years, however, it remains extremely challenging to automatically equip such environment with realistic human bodies. Existing work utilizes images, depth or semantic maps to represent the scene, and parametric human models to represent 3D bodies. While being straightforward, their generated human-scene interactions are often lack of naturalness and physical plausibility. Our key observation is that humans interact with the world through body-scene contact. To synthesize realistic human-scene interactions, it is essential to effectively represent the physical contact and proximity between the body and the world. To that end, we propose a novel interaction generation method, named PLACE (Proximity Learning of Articulation and Contact in 3D Environments), which explicitly models the proximity between the human body and the 3D scene around it. Specifically, given a set of basis points on a scene mesh, we leverage a conditional variational autoencoder to synthesize the minimum distances from the basis points to the human body surface. The generated proximal relationship exhibits which region of the scene is in contact with the person. Furthermore, based on such synthesized proximity, we are able to effectively obtain expressive 3D human bodies that interact with the 3D scene naturally. Our perceptual study shows that PLACE significantly improves the state-of-the-art method, approaching the realism of real human-scene interaction. We believe our method makes an important step towards the fully automatic synthesis of realistic 3D human bodies in 3D scenes. The code and model are available for research at https://sanweiliti.github.io/PLACE/PLACE.html., Comment: Accepted by 3DV 2020, camera ready version with appendix