Search

Sketch, a powerful artistic technique to capture essential visual information about real-world objects, is increasingly gaining attention in the image synthesis field. However, evaluating the quality of synthesized sketches presents unique unsolved challenges. Current evaluation methods for sketch synthesis are inadequate due to the lack of a unified benchmark dataset, over-reliance on classification accuracy for recognizability, and unfair evaluation of sketches with different levels of simplification. To address these issues, we introduce SketchRef, a benchmark dataset comprising 4 categories of reference photos--animals, human faces, human bodies, and common objects--alongside novel evaluation metrics. Considering that classification accuracy is insufficient to measure the structural consistency between a sketch and its reference photo, we propose the mean Object Keypoint Similarity (mOKS) metric, utilizing pose estimation to assess structure-level recognizability. To ensure fair evaluation sketches with different simplification levels, we propose a recognizability calculation method constrained by simplicity. We also collect 8K responses from art enthusiasts, validating the effectiveness of our proposed evaluation methods. We hope this work can provide a comprehensive evaluation of sketch synthesis algorithms, thereby aligning their performance more closely with human understanding.

The study of state-to-state spin-exchange collisions in the vicinity of $p$-wave Feshbach resonances offer great opportunities to explore many-body interactions and novel quantum phases. Here, we report the observation of a spin-exchange collision near a $p$-wave Feshbach resonance within a mixture of the lowest and third-lowest hyperfine states of $^6$Li atoms. The spin-exchange interaction is observed over a range of ten gausses and produces a pair of atoms in the second-lowest hyperfine states that are captured by a deep optical dipole trap. We apply a coupled-channel method to calculate the scattering properties of this system. We find that the $p$-wave resonance exhibits a low inelastic collision rate and a broad resonance profile, which is due to the modification by the accompanying spin-exchange collisions. These findings open up new possibilities for the creation of long-lived, strongly interacting $p$-wave Fermi gases.

Single-image novel view synthesis is a challenging and ongoing problem that aims to generate an infinite number of consistent views from a single input image. Although significant efforts have been made to advance the quality of generated novel views, less attention has been paid to the expansion of the underlying scene representation, which is crucial to the generation of realistic novel view images. This paper proposes SinMPI, a novel method that uses an expanded multiplane image (MPI) as the 3D scene representation to significantly expand the perspective range of MPI and generate high-quality novel views from a large multiplane space. The key idea of our method is to use Stable Diffusion to generate out-of-view contents, project all scene contents into an expanded multiplane image according to depths predicted by monocular depth estimators, and then optimize the multiplane image under the supervision of pseudo multi-view data generated by a depth-aware warping and inpainting module. Both qualitative and quantitative experiments have been conducted to validate the superiority of our method to the state of the art. Our code and data are available at https://github.com/TrickyGo/SinMPI., Comment: 10 pages

This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing, leveraging the power of scale. Drawing inspiration from recent advances in 3D large-scale representation learning, we recognize that model performance is more influenced by scale than by intricate design. Therefore, we present Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the overall performance after scaling, such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns. This principle enables significant scaling, expanding the receptive field from 16 to 1024 points while remaining efficient (a 3x increase in processing speed and a 10x improvement in memory efficiency compared with its predecessor, PTv2). PTv3 attains state-of-the-art results on over 20 downstream tasks that span both indoor and outdoor scenarios. Further enhanced with multi-dataset joint training, PTv3 pushes these results to a higher level., Comment: CVPR 2024, code available at Pointcept (https://github.com/Pointcept/PointTransformerV3)

We present GeGnn, a learning-based method for computing the approximate geodesic distance between two arbitrary points on discrete polyhedra surfaces with constant time complexity after fast precomputation. Previous relevant methods either focus on computing the geodesic distance between a single source and all destinations, which has linear complexity at least or require a long precomputation time. Our key idea is to train a graph neural network to embed an input mesh into a high-dimensional embedding space and compute the geodesic distance between a pair of points using the corresponding embedding vectors and a lightweight decoding function. To facilitate the learning of the embedding, we propose novel graph convolution and graph pooling modules that incorporate local geodesic information and are verified to be much more effective than previous designs. After training, our method requires only one forward pass of the network per mesh as precomputation. Then, we can compute the geodesic distance between a pair of points using our decoding function, which requires only several matrix multiplications and can be massively parallelized on GPUs. We verify the efficiency and effectiveness of our method on ShapeNet and demonstrate that our method is faster than existing methods by orders of magnitude while achieving comparable or better accuracy. Additionally, our method exhibits robustness on noisy and incomplete meshes and strong generalization ability on out-of-distribution meshes. The code and pretrained model can be found on https://github.com/IntelligentGeometry/GeGnn., Comment: SIGGRAPH Asia 2023, Journal Track

Mesh repair is a long-standing challenge in computer graphics and related fields. Converting defective meshes into watertight manifold meshes can greatly benefit downstream applications such as geometric processing, simulation, fabrication, learning, and synthesis. In this work, we first introduce three visual measures for visibility, orientation, and openness, based on ray-tracing. We then present a novel mesh repair framework that incorporates visual measures with several critical steps, i.e., open surface closing, face reorientation, and global optimization, to effectively repair defective meshes, including gaps, holes, self-intersections, degenerate elements, and inconsistent orientations. Our method reduces unnecessary mesh complexity without compromising geometric accuracy or visual quality while preserving input attributes such as UV coordinates for rendering. We evaluate our approach on hundreds of models randomly selected from ShapeNet and Thingi10K, demonstrating its effectiveness and robustness compared to existing approaches.

Although the recent rapid evolution of 3D generative neural networks greatly improves 3D shape generation, it is still not convenient for ordinary users to create 3D shapes and control the local geometry of generated shapes. To address these challenges, we propose a diffusion-based 3D generation framework -- locally attentional SDF diffusion, to model plausible 3D shapes, via 2D sketch image input. Our method is built on a two-stage diffusion model. The first stage, named occupancy-diffusion, aims to generate a low-resolution occupancy field to approximate the shape shell. The second stage, named SDF-diffusion, synthesizes a high-resolution signed distance field within the occupied voxels determined by the first stage to extract fine geometry. Our model is empowered by a novel view-aware local attention mechanism for image-conditioned shape generation, which takes advantage of 2D image patch features to guide 3D voxel feature learning, greatly improving local controllability and model generalizability. Through extensive experiments in sketch-conditioned and category-conditioned 3D shape generation tasks, we validate and demonstrate the ability of our method to provide plausible and diverse 3D shapes, as well as its superior controllability and generalizability over existing work. Our code and trained models are available at https://zhengxinyang.github.io/projects/LAS-Diffusion.html, Comment: Accepted to SIGGRAPH 2023 (Journal version)

We propose octree-based transformers, named OctFormer, for 3D point cloud learning. OctFormer can not only serve as a general and effective backbone for 3D point cloud segmentation and object detection but also have linear complexity and is scalable for large-scale point clouds. The key challenge in applying transformers to point clouds is reducing the quadratic, thus overwhelming, computation complexity of attentions. To combat this issue, several works divide point clouds into non-overlapping windows and constrain attentions in each local window. However, the point number in each window varies greatly, impeding the efficient execution on GPU. Observing that attentions are robust to the shapes of local windows, we propose a novel octree attention, which leverages sorted shuffled keys of octrees to partition point clouds into local windows containing a fixed number of points while permitting shapes of windows to change freely. And we also introduce dilated octree attention to expand the receptive field further. Our octree attention can be implemented in 10 lines of code with open-sourced libraries and runs 17 times faster than other point cloud attentions when the point number exceeds 200k. Built upon the octree attention, OctFormer can be easily scaled up and achieves state-of-the-art performances on a series of 3D segmentation and detection benchmarks, surpassing previous sparse-voxel-based CNNs and point cloud transformers in terms of both efficiency and effectiveness. Notably, on the challenging ScanNet200 dataset, OctFormer outperforms sparse-voxel-based CNNs by 7.3 in mIoU. Our code and trained models are available at https://wang-ps.github.io/octformer., Comment: SIGGRAPH 2023, Journal Track

Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore features at the masked pixels, such as colors, the existing 3D MAE works reconstruct the missing geometry only, i.e, the location of the masked points. In contrast to previous studies, we advocate that point location recovery is inessential and restoring intrinsic point features is much superior. To this end, we propose to ignore point position reconstruction and recover high-order features at masked points including surface normals and surface variations, through a novel attention-based decoder which is independent of the encoder design. We validate the effectiveness of our pretext task and decoder design using different encoder structures for 3D training and demonstrate the advantages of our pretrained networks on various point cloud analysis tasks., Comment: Published in ICLR 2024

The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this work, we introduce a pretrained 3D backbone, called {\SST}, for 3D indoor scene understanding. We design a 3D Swin transformer as our backbone network, which enables efficient self-attention on sparse voxels with linear memory complexity, making the backbone scalable to large models and datasets. We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network performance. We pretrained a large {\SST} model on a synthetic Structured3D dataset, which is an order of magnitude larger than the ScanNet dataset. Our model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets, but also outperforms state-of-the-art methods on downstream tasks with +2.3 mIoU and +2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation, +1.8 mIoU on ScanNet segmentation (val), +1.9 mAP@0.5 on ScanNet detection, and +8.1 mAP@0.5 on S3DIS detection. A series of extensive ablation studies further validate the scalability, generality, and superior performance enabled by our approach. The code and models are available at https://github.com/microsoft/Swin3D ., Comment: Project page: https://yukichiii.github.io/project/swin3D/swin3D.html

Self-supervised representation learning follows a paradigm of withholding some part of the data and tasking the network to predict it from the remaining part. Among many techniques, data augmentation lies at the core for creating the information gap. Towards this end, masking has emerged as a generic and powerful tool where content is withheld along the sequential dimension, e.g., spatial in images, temporal in audio, and syntactic in language. In this paper, we explore the orthogonal channel dimension for generic data augmentation by exploiting precision redundancy. The data for each channel is quantized through a non-uniform quantizer, with the quantized value sampled randomly within randomly sampled quantization bins. From another perspective, quantization is analogous to channel-wise masking, as it removes the information within each bin, but preserves the information across bins. Our approach significantly surpasses existing generic data augmentation methods, while showing on par performance against modality-specific augmentations. We comprehensively evaluate our approach on vision, audio, 3D point clouds, as well as the DABS benchmark which is comprised of various data modalities. The code is available at https: //github.com/microsoft/random_quantize., Comment: Accepted by ICCV 2023. The code is available at https: //github.com/microsoft/random_quantize

Ultracold atomic gases provide a controllable system to study the inelastic processes for three-body systems, where the three-body recombination rate depends on the scattering length scaling. Such scalings have been confirmed in bosonic systems with various interaction strengths, but their existence with fermionic atoms remains elusive. In this work, we report on an experimental investigation of the scaling law for the three-body atomic loss rate $L_3$ in a two-component $^6$Li Fermi gas with the scattering length $a<0$. The scaling law is validated within a certain range of $a$ near the narrow $s$-wave Feshbach resonance, where $L_3\propto T|a|^{2.60(5)}$, and $T$ is the gas temperature. The scaling law is observed to have an upper and a lower bound in terms of the scattering length. For the upper bound, when $a\rightarrow \infty$, the power-law scaling is suppressed by the unitary behavior of the resonance caused by the strong three-body collisions. For the lower bound, $a\rightarrow 0$, the finite range effect modifies the scaling law by the effective scattering length $L_e$. These results indicate that the three-body recombination rate in a fermionic system could be characterized by the scaling law associated with the generalized Efimov physics., Comment: 11 pages, 3 figures, 1 table

We present a StyleGAN2-based deep learning approach for 3D shape generation, called SDF-StyleGAN, with the aim of reducing visual and geometric dissimilarity between generated shapes and a shape collection. We extend StyleGAN2 to 3D generation and utilize the implicit signed distance function (SDF) as the 3D shape representation, and introduce two novel global and local shape discriminators that distinguish real and fake SDF values and gradients to significantly improve shape geometry and visual quality. We further complement the evaluation metrics of 3D generative models with the shading-image-based Fr\'echet inception distance (FID) scores to better assess visual quality and shape distribution of the generated shapes. Experiments on shape generation demonstrate the superior performance of SDF-StyleGAN over the state-of-the-art. We further demonstrate the efficacy of SDF-StyleGAN in various tasks based on GAN inversion, including shape reconstruction, shape completion from partial point clouds, single-view image-based shape generation, and shape style editing. Extensive ablation studies justify the efficacy of our framework design. Our code and trained models are available at https://github.com/Zhengxinyang/SDF-StyleGAN., Comment: Accepted to Computer Graphics Forum (SGP), 2022

The many-body physics in the dimensional crossover regime attracts much attention in cold atom experiments, but yet to explore systematically. One of the technical difficulties existed in the experiments is the lack of the experimental technique to quantitatively tune the atom occupation ratio of the different lattice bands. In this letter, we report such techniques in a process of transferring a 3D Fermi gas into a 1D optical lattice, where the capability of tuning the occupation of the energy band is realized by varying the trapping potentials of the optical dipole trap (ODT) and the lattice, respectively. We could tune a Fermi gas with the occupation in the lowest band from unity to 50$\%$ quantitatively. This provides a route to experimentally study the dependence of many-body interaction on the dimensionality in a Fermi gas.

We present an adaptive deep representation of volumetric fields of 3D shapes and an efficient approach to learn this deep representation for high-quality 3D shape reconstruction and auto-encoding. Our method encodes the volumetric field of a 3D shape with an adaptive feature volume organized by an octree and applies a compact multilayer perceptron network for mapping the features to the field value at each 3D position. An encoder-decoder network is designed to learn the adaptive feature volume based on the graph convolutions over the dual graph of octree nodes. The core of our network is a new graph convolution operator defined over a regular grid of features fused from irregular neighboring octree nodes at different levels, which not only reduces the computational and memory cost of the convolutions over irregular neighboring octree nodes, but also improves the performance of feature learning. Our method effectively encodes shape details, enables fast 3D shape reconstruction, and exhibits good generality for modeling 3D shapes out of training categories. We evaluate our method on a set of reconstruction tasks of 3D shapes and scenes and validate its superiority over other existing approaches. Our code, data, and trained models are available at https://wang-ps.github.io/dualocnn., Comment: Accepted to SIGGRAPH 2022

The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data. For the unlabeled data, we present a novel multilevel consistency loss to enforce consistency of network predictions between perturbed copies of a 3D shape at multiple levels: point-level, part-level, and hierarchical level. For the labeled data, we develop a simple yet effective part substitution scheme to augment the labeled 3D shapes with more structural variations to enhance training. Our method has been extensively validated on the task of 3D object semantic segmentation on PartNet and ShapeNetPart, and indoor scene semantic segmentation on ScanNet. It exhibits superior performance to existing semi-supervised and unsupervised pre-training 3D approaches. Our code and trained models are publicly available at https://github.com/isunchy/semi_supervised_3d_segmentation., Comment: Computational Visual Media 2022. Project page: https://isunchy.github.io/projects/semi_supervised_3d_segmentation.html

Sparse voxel-based 3D convolutional neural networks (CNNs) are widely used for various 3D vision tasks. Sparse voxel-based 3D CNNs create sparse non-empty voxels from the 3D input and perform 3D convolution operations on them only. We propose a simple yet effective padding scheme --- interpolation-aware padding to pad a few empty voxels adjacent to the non-empty voxels and involve them in the 3D CNN computation so that all neighboring voxels exist when computing point-wise features via the trilinear interpolation. For fine-grained 3D vision tasks where point-wise features are essential, like semantic segmentation and 3D detection, our network achieves higher prediction accuracy than the existing networks using the nearest neighbor interpolation or the normalized trilinear interpolation with the zero-padding or the octree-padding scheme. Through extensive comparisons on various 3D segmentation and detection tasks, we demonstrate the superiority of 3D sparse CNNs with our padding scheme in conjunction with feature interpolation.

Three-body recombination is a phenomenon common in atomic and molecular collisions, producing heating in the system. However, we find the cooling effect of the three-body recombination of a 6Li Fermi gas near its s-wave narrow Feshbach resonance. Such counter-intuitive behavior is explained as follows, the threshold energy of the quasi-bounded Feshbach molecule acts as the knife of cooling, expelling the scattering atoms with selected kinetic energy from the trap. When the threshold energy happens to be larger than 3/2kBT, each lost atom in the three-body recombination process has more than 3kBT energy which results in cooling. The best cooling is found with the threshold energy set at about 3kBT, consistent with a theoretical model. The three-body recombination induced cooling raises potential applications for cooling complex atomic systems.

Multilayer perceptrons (MLPs) have been successfully used to represent 3D shapes implicitly and compactly, by mapping 3D coordinates to the corresponding signed distance values or occupancy values. In this paper, we propose a novel positional encoding scheme, called Spline Positional Encoding, to map the input coordinates to a high dimensional space before passing them to MLPs, for helping to recover 3D signed distance fields with fine-scale geometric details from unorganized 3D point clouds. We verified the superiority of our approach over other positional encoding schemes on tasks of 3D shape reconstruction from input point clouds and shape space learning. The efficacy of our approach extended to image reconstruction is also demonstrated and evaluated., Comment: Accepted by IJCAI 2021; Code: https://github.com/microsoft/SplinePosEnc

The variable source OGLE-UCXB-01 is the first OGLE-discovered ultracompact X-ray binary (UCXB). The 12-year long-term OGLE optical photometry of this source shows a period of P= 12.8 min and a fast period decreasing rate Pdot= -9.2E-11 s s^-1. At a luminosity of L_X ~ 4E33 erg s^-1, its X-ray emission is also variable and correlated with the optical variability. To determine the nature of this variable source, specifically the masses and types of its binary components, we consider first an attractive possibility that the optical variation is due to the secondary's ellipsoidal variation and a strong gravitational wave emission drives the orbital decay. However, we can not find an allowable solution to the secondary that satisfies simultaneously the three constraints: an ultra-tight orbit, the bright absolute magnitude, and the large amplitude of the brightness variation. Moreover, the inferred mass transfer rate is too high. This scenario is therefore ruled out. We then find the system is fully consistent with an "intermediate polar" model, in which the optical and X-ray emission comes from a magnetized white dwarf (WD) accreting from a low-mass (<~ 0.7 M_sun) main-sequence secondary. The observed period decay is the accretion-driven spin-up of the WD. The WD spin period is 12.8 min and the orbital period is shorter than 10 hr. The method presented here can be applied to other UCXB candidates or impostors with time-domain data available only., Comment: 7 pages, 7 figures, accepted for publication on ApJ

Encoder-decoder models have made great progress on handwritten mathematical expression recognition recently. However, it is still a challenge for existing methods to assign attention to image features accurately. Moreover, those encoder-decoder models usually adopt RNN-based models in their decoder part, which makes them inefficient in processing long $\LaTeX{}$ sequences. In this paper, a transformer-based decoder is employed to replace RNN-based ones, which makes the whole model architecture very concise. Furthermore, a novel training strategy is introduced to fully exploit the potential of the transformer in bidirectional language modeling. Compared to several methods that do not use data augmentation, experiments demonstrate that our model improves the ExpRate of current state-of-the-art methods on CROHME 2014 by 2.23%. Similarly, on CROHME 2016 and CROHME 2019, we improve the ExpRate by 1.92% and 2.28% respectively., Comment: Accept by ICDAR 2021