CLCindy Le

Cindy Le

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Cindy Le has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    EucliDreamer: Fast and High-Quality Texturing for 3D Models with Depth-Conditioned Stable Diffusion

    by Cindy Le, Congrui Hetang, Chendi Lin, Ang Cao, Yihui He

    We present EucliDreamer, a simple and effective method to generate textures for 3D models given text prompts and meshes. The texture is parametrized as an implicit function on the 3D surface, which is optimized with the Score Distillation Sampling (SDS) process and differentiable rendering. To generate high-quality textures, we leverage a depth-conditioned Stable Diffusion model guided by the depth image rendered from the mesh. We test our approach on 3D models in Objaverse and conducted a user study, which shows its superior quality compared to existing texturing methods like Text2Tex. In addition, our method converges 2 times faster than DreamFusion. Through text prompting, textures of diverse art styles can be produced. We hope Euclidreamer proides a viable solution to automate a labor-intensive stage in 3D content creation.

  • Open Access

    Segment Anything Model for Road Network Graph Extraction

    by Congrui Hetang, Haoru Xue, Cindy Le, Tianwei Yue, Wenping Wang, Yihui He

    We propose SAM-Road, an adaptation of the Segment Anything Model (SAM) for extracting large-scale, vectorized road network graphs from satellite imagery. To predict graph geometry, we formulate it as a dense semantic segmentation task, leveraging the inherent strengths of SAM. The image encoder of SAM is fine-tuned to produce probability masks for roads and intersections, from which the graph vertices are extracted via simple non-maximum suppression. To predict graph topology, we designed a lightweight transformer-based graph neural network, which leverages the SAM image embeddings to estimate the edge existence probabilities between vertices. Our approach directly predicts the graph vertices and edges for large regions without expensive and complex post-processing heuristics, and is capable of building complete road network graphs spanning multiple square kilometers in a matter of seconds. With its simple, straightforward, and minimalist design, SAM-Road achieves comparable accuracy with the state-of-the-art method RNGDet++, while being 40 times faster on the City-scale dataset. We thus demonstrate the power of a foundational vision model when applied to a graph learning task. The code is available at https://github.com/htcr/sam_road.


  • Open Access

    EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth

    by Cindy Le, Congrui Hetang, Chendi Lin, Ang Cao, Yihui He

    This paper presents a novel method to generate textures for 3D models given text prompts and 3D meshes. Additional depth information is taken into account to perform the Score Distillation Sampling (SDS) process with depth conditional Stable Diffusion. We ran our model over the open-source dataset Objaverse and conducted a user study to compare the results with those of various 3D texturing methods. We have shown that our model can generate more satisfactory results and produce various art styles for the same object. In addition, we achieved faster time when generating textures of comparable quality. We also conduct thorough ablation studies of how different factors may affect generation quality, including sampling steps, guidance scale, negative prompts, data augmentation, elevation range, and alternatives to SDS.

  • Open Access

    Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers

    by Hai Phan, Cindy Le, Vu Le, Yihui He, Anh Totti Nguyen

    Most face identification approaches employ a Siamese neural network to compare two images at the image embedding level. Yet, this technique can be subject to occlusion (e.g. faces with masks or sunglasses) and out-of-distribution data. DeepFace-EMD (Phan et al. 2022) reaches state-of-the-art accuracy on out-of-distribution data by first comparing two images at the image level, and then at the patch level. Yet, its later patch-wise re-ranking stage admits a large $O(n^3 \log n)$ time complexity (for $n$ patches in an image) due to the optimal transport optimization. In this paper, we propose a novel, 2-image Vision Transformers (ViTs) that compares two images at the patch level using cross-attention. After training on 2M pairs of images on CASIA Webface (Yi et al. 2014), our model performs at a comparable accuracy as DeepFace-EMD on out-of-distribution data, yet at an inference speed more than twice as fast as DeepFace-EMD (Phan et al. 2022). In addition, via a human study, our model shows promising explainability through the visualization of cross-attention. We believe our work can inspire more explorations in using ViTs for face identification.

  • Open Access

    Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks

    by Yihui He, Jianing Qian, Jianren Wang, Cindy X. Le, Congrui Hetang, Qi Lyu, Wenping Wang, Tianwei Yue

    Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regular convolutions into depthwise separable convolutions while maintaining high accuracy. We show our approach can be further generalized to the multi-channel and multi-layer cases, based on Generalized Singular Value Decomposition (GSVD) [59]. We conduct thorough experiments with the latest ShuffleNet V2 model [47] on both random synthesized dataset and a large-scale image recognition dataset: ImageNet [10]. Our approach outperforms channel decomposition [73] on all datasets. More importantly, our approach improves the Top-1 accuracy of ShuffleNet V2 by ~2%.

  • Open Access

    Enhancing Abstractive Summarization with Extracted Knowledge Graphs and Multi-Source Transformers

    by Tong Chen, Xuewei Wang, Tianwei Yue, Xiaoyu Bai, Cindy X. Le, Wenping Wang

    As the popularity of large language models (LLMs) has risen over the course of the last year, led by GPT-3/4 and especially its productization as ChatGPT, we have witnessed the extensive application of LLMs to text summarization. However, LLMs do not intrinsically have the power to verify the correctness of the information they supply and generate. This research introduces a novel approach to abstractive summarization, aiming to address the limitations of LLMs in that they struggle to understand the truth. The proposed method leverages extracted knowledge graph information and structured semantics as a guide for summarization. Building upon BART, one of the state-of-the-art sequence-to-sequence pre-trained LLMs, multi-source transformer modules are developed as an encoder, which are capable of processing textual and graphical inputs. Decoding is performed based on this enriched encoding to enhance the summary quality. The Wiki-Sum dataset, derived from Wikipedia text dumps, is introduced for evaluation purposes. Comparative experiments with baseline models demonstrate the strengths of the proposed approach in generating informative and relevant summaries. We conclude by presenting our insights into utilizing LLMs with graph external information, which will become a powerful aid towards the goal of factually correct and verified LLMs.