Lei Li

Selected Publications

1. CVPR

   MeshArt: Generating Articulated Meshes with Structure-Guided Transformers

   Daoyi Gao, Yawar Siddiqui,  Lei Li, and Angela Dai

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025

   Abstract PDF Video Website

   Articulated 3D object generation is fundamental for creating realistic, functional, and interactable virtual assets which are not simply static. We introduce MeshArt, a hierarchical transformer-based approach to generate articulated 3D meshes with clean, compact geometry, reminiscent of human-crafted 3D models. We approach articulated mesh generation in a part-by-part fashion across two stages. First, we generate a high-level articulation-aware object structure; then, based on this structural information, we synthesize each part’s mesh faces. Key to our approach is modeling both articulation structures and part meshes as sequences of quantized triangle embeddings, leading to a unified hierarchical framework with transformers for autoregressive generation. Object part structures are first generated as their bounding primitives and articulation modes; a second transformer, guided by these articulation structures, then generates each part’s mesh triangles. To ensure coherency among generated parts, we introduce structure-guided conditioning that also incorporates local part mesh connectivity. MeshArt shows significant improvements over state of the art, with 57.1% improvement in structure coverage and a 209-point improvement in mesh generation FID.

2. CVPR

   LT3SD: Latent Trees for 3D Scene Diffusion

   Quan Meng,  Lei Li, Matthias Nießner, and Angela Dai

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025

   Abstract PDF Video Code Website

   We present LT3SD, a novel latent diffusion model for large-scale 3D scene generation. Recent advances in diffusion models have shown impressive results in 3D object generation, but are limited in spatial extent and quality when extended to 3D scenes. To generate complex and diverse 3D scene structures, we introduce a latent tree representation to effectively encode both lower-frequency geometry and higher-frequency detail in a coarse-to-fine hierarchy. We can then learn a generative diffusion process in this latent 3D scene space, modeling the latent components of a scene at each resolution level. To synthesize large-scale scenes with varying sizes, we train our diffusion model on scene patches and synthesize arbitrary-sized output 3D scenes through shared diffusion generation across multiple scene patches. Through extensive experiments, we demonstrate the efficacy and benefits of LT3SD for large-scale, high-quality unconditional 3D scene generation and for probabilistic completion for partial scene observations.

3. CVPR

   GenZI: Zero-Shot 3D Human-Scene Interaction Generation

   Lei Li, and Angela Dai

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024

   Abstract PDF Supplement Video Code Website

   Can we synthesize 3D humans interacting with scenes without learning from any 3D human-scene interaction data? We propose GenZI, the first zero-shot approach to generating 3D human-scene interactions. Key to GenZI is our distillation of interaction priors from large vision-language models (VLMs), which have learned a rich semantic space of 2D human-scene compositions. Given a natural language description and a coarse point location of the desired interaction in a 3D scene, we first leverage VLMs to imagine plausible 2D human interactions inpainted into multiple rendered views of the scene. We then formulate a robust iterative optimization to synthesize the pose and shape of a 3D human model in the scene, guided by consistency with the 2D interaction hypotheses. In contrast to existing learning-based approaches, GenZI circumvents the conventional need for captured 3D interaction data, and allows for flexible control of the 3D interaction synthesis with easy-to-use text prompts. Extensive experiments show that our zero-shot approach has high flexibility and generality, making it applicable to diverse scene types, including both indoor and outdoor environments.

4. ECCV

   To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learning

   Souhail Hadgi,  Lei Li, and Maks Ovsjanikov

   In European Conference on Computer Vision 2024

   Abstract PDF Supplement

   Transfer learning has long been a key factor in the advancement of many fields including 2D image analysis. Unfortunately, its applicability in 3D data processing has been relatively limited. While several approaches for 3D transfer learning have been proposed in recent literature, with contrastive learning gaining particular prominence, most existing methods in this domain have only been studied and evaluated in limited scenarios. Most importantly, there is currently a lack of principled understanding of both when and why 3D transfer learning methods are applicable. Remarkably, even the applicability of standard supervised pre-training is poorly understood. In this work, we conduct the first in-depth quantitative and qualitative investigation of supervised and contrastive pre-training strategies and their utility in downstream 3D tasks. We demonstrate that layer-wise analysis of learned features provides significant insight into the downstream utility of trained networks. Informed by this analysis, we propose a simple geometric regularization strategy, which improves the transferability of supervised pre-training. Our work thus sheds light onto both the specific challenges of 3D transfer learning, as well as strategies to overcome them.

5. CVPR

   Generalizable Local Feature Pre-training for Deformable Shape Analysis

   Souhaib Attaiki,  Lei Li, and Maks Ovsjanikov

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023

   Abstract PDF Code Highlight Presentation

   Transfer learning is fundamental for addressing problems in settings with little training data. While several transfer learning approaches have been proposed in 3D, unfortunately, these solutions typically operate on an entire 3D object or even scene-level and thus, as we show, fail to generalize to new classes, such as deformable organic shapes. In addition, there is currently a lack of understanding of what makes pre-trained features transferable across significantly different 3D shape categories. In this paper, we make a step toward addressing these challenges. First, we analyze the link between feature locality and transferability in tasks involving deformable 3D objects, while also comparing different backbones and losses for local feature pre-training. We observe that with proper training, learned features can be useful in such tasks, but, crucially, only with an appropriate choice of the receptive field size. We then propose a differentiable method for optimizing the receptive field within 3D transfer learning. Jointly, this leads to the first learnable features that can successfully generalize to unseen classes of 3D shapes such as humans and animals. Our extensive experiments show that this approach leads to state-of-the-art results on several downstream tasks such as segmentation, shape correspondence, and classification. Our code is available at https://github.com/pvnieo/vader.

6. NeurIPS

   Learning Multi-resolution Functional Maps with Spectral Attention for Robust Shape Matching

   Lei Li, Nicolas Donati, and Maks Ovsjanikov

   In Neural Information Processing Systems 2022

   Abstract PDF Code Spotlight Presentation

   In this work, we present a novel non-rigid shape matching framework based on multi-resolution functional maps with spectral attention. Existing functional map learning methods all rely on the critical choice of the spectral resolution hyperparameter, which can severely affect the overall accuracy or lead to overfitting, if not chosen carefully. In this paper, we show that spectral resolution tuning can be alleviated by introducing spectral attention. Our framework is applicable in both supervised and unsupervised settings, and we show that it is possible to train the network so that it can adapt the spectral resolution, depending on the given shape input. More specifically, we propose to compute multi-resolution functional maps that characterize correspondence across a range of spectral resolutions, and introduce a spectral attention network that helps to combine this representation into a single coherent final correspondence. Our approach is not only accurate with near-isometric input, for which a high spectral resolution is typically preferred, but also robust and able to produce reasonable matching even in the presence of significant non-isometric distortion, which poses great challenges to existing methods. We demonstrate the superior performance of our approach through experiments on a suite of challenging near-isometric and non-isometric shape matching benchmarks.

7. TVCG

   WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration

   Lei Li, Hongbo Fu, and Maks Ovsjanikov

   IEEE Transactions on Visualization and Computer Graphics 2022

   Abstract PDF Code

   In this work, we present a novel method called WSDesc to learn 3D local descriptors in a weakly supervised manner for robust point cloud registration. Our work builds upon recent 3D CNN-based descriptor extractors, which leverage a voxel-based representation to parameterize local geometry of 3D points. Instead of using a predefined fixed-size local support in voxelization, we propose to learn the optimal support in a data-driven manner. To this end, we design a novel differentiable voxelization layer that can back-propagate the gradient to the support size optimization. To train the extracted descriptors, we propose a novel registration loss based on the deviation from rigidity of 3D transformations, and the loss is weakly supervised by the prior knowledge that the input point clouds have partial overlap, without requiring ground-truth alignment information. Through extensive experiments, we show that our learned descriptors yield superior performance on existing geometric registration benchmarks.

8. CVPR

   PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency

   Xuyang Bai, Zixin Luo, Lei Zhou, Hongkai Chen,  Lei Li, Zeyu Hu, Hongbo Fu, and Chiew-Lan Tai

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021

   Abstract PDF Code

   Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration. Despite the increasing popularity of introducing deep learning methods in this field, spatial consistency, which is essentially established by a Euclidean transformation between point clouds, has received almost no individual attention in existing learning frameworks. In this paper, we present PointDSC, a novel deep neural network that explicitly incorporates spatial consistency for pruning outlier correspondences. First, we propose a nonlocal feature aggregation module, weighted by both feature and spatial coherence, for feature embedding of the input correspondences. Second, we formulate a differentiable spectral matching module, supervised by pairwise spatial compatibility, to estimate the inlier confidence of each correspondence from the embedded features. With modest computation cost, our method outperforms the state-of-the-art hand-crafted and learning-based outlier rejection approaches on several real-world datasets by a significant margin. We also show its wide applicability by combining PointDSC with different 3D local descriptors.

9. CVPR

   End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds

   Lei Li, Siyu Zhu, Hongbo Fu, Ping Tan, and Chiew-Lan Tai

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020

   Abstract PDF Code

   In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.

10. TVCG

    Sketch-R2CNN: An RNN-Rasterization-CNN Architecture for Vector Sketch Recognition

    Lei Li, Changqing Zou, Youyi Zheng, Qingkun Su, Hongbo Fu, and Chiew-Lan Tai

    IEEE Transactions on Visualization and Computer Graphics 2020

    Abstract PDF Code

    Sketches in existing large-scale datasets like the recent QuickDraw collection are often stored in a vector format, with strokes consisting of sequentially sampled points. However, most existing sketch recognition methods rasterize vector sketches as binary images and then adopt image classification techniques. In this article, we propose a novel end-to-end single-branch network architecture RNN-Rasterization-CNN (Sketch-R2CNN for short) to fully leverage the vector format of sketches for recognition. Sketch-R2CNN takes a vector sketch as input and uses an RNN for extracting per-point features in the vector space. We then develop a neural line rasterization module to convert the vector sketch and the per-point features to multi-channel point feature maps, which are subsequently fed to a CNN for extracting convolutional features in the pixel space. Our neural line rasterization module is designed in a differentiable way for end-to-end learning. We perform experiments on existing large-scale sketch recognition datasets and show that the RNN-Rasterization design brings consistent improvement over CNN baselines and that Sketch-R2CNN substantially outperforms the state-of-the-art methods.

11. CG&A

    Fast Sketch Segmentation and Labeling with Deep Learning

    Lei Li, Hongbo Fu, and Chiew-Lan Tai

    IEEE Computer Graphics and Applications 2018

    Abstract PDF Video Code Best Paper Award Runner-Up

    We present a simple and efficient method based on deep learning to automatically decompose sketched objects into semantically valid parts. We train a deep neural network to transfer existing segmentations and labelings from three-dimensional (3-D) models to freehand sketches without requiring numerous well-annotated sketches as training data. The network takes the binary image of a sketched object as input and produces a corresponding segmentation map with per-pixel labelings as output. A subsequent postprocess procedure with multilabel graph cuts further refines the segmentation and labeling result. We validate our proposed method on two sketch datasets. Experiments show that our method outperforms the state-of-the-art method in terms of segmentation and labeling accuracy and is significantly faster, enabling further integration in interactive drawing systems. We demonstrate the efficiency of our method in a sketch-based modeling application that automatically transforms input sketches into 3-D models by part assembly.