Search Results for author:
Found 69 papers, 27 papers with code
DeepSeek-V3 Technical Report
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
A Review of Human Emotion Synthesis Based on Generative Technology
Specifically, this review will first present the review methodology, the emotion models involved, the mathematical principles of generative models, and the datasets used.
3D Scene Graph Guided Vision-Language Pre-training
The pre-training objectives include: 1) Scene graph-guided contrastive learning, which leverages the strong correlation between 3D scene graphs and natural language to align 3D objects with textual features at various fine-grained levels; and 2) Masked modality learning, which uses cross-modality information to reconstruct masked words and 3D objects.
Point Cloud Unsupervised Pre-training via 3D Gaussian Splatting
Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited.
GSurf: 3D Reconstruction via Signed Distance Fields with Direct Gaussian Supervision
However, these approaches often suffer from slow training and rendering speeds compared to 3D Gaussian splatting (3DGS).
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS
Our method leverages the observation that transparent surfaces induce local extreme values in the learned distance fields during neural volumetric rendering, contrasting with opaque surfaces that align with zero level sets.
Quasi-Medial Distance Field (Q-MDF): A Robust Method for Approximating and Discretizing Neural Medial Axis
The medial axis, a lower-dimensional shape descriptor, plays an important role in the field of digital geometry processing.
DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fields
Unsigned distance fields (UDFs) allow for the representation of models with complex topologies, but extracting accurate zero level sets from these fields poses significant challenges, particularly in preserving topological accuracy and capturing fine geometric details.
Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning
For DL training, we deployed the Fire-Flyer 2 with 10, 000 PCIe A100 GPUs, achieved performance approximating the DGX-A100 while reducing costs by half and energy consumption by 40%.
ByCAN: Reverse Engineering Controller Area Network (CAN) Messages from Bit to Byte Level
As the primary standard protocol for modern cars, the Controller Area Network (CAN) is a critical research target for automotive cybersecurity threats and autonomous applications.
PP-TIL: Personalized Planning for Autonomous Driving with Instance-based Transfer Imitation Learning
We initially train a pre-trained model using large-scale expert data.
Generative Technology for Human Emotion Recognition: A Scope Review
Finally, the review will outline future research directions, emphasizing the potential of generative models to advance the field of emotion recognition and enhance the emotional intelligence of AI systems.
Consistent Point Orientation for Manifold Surfaces via Boundary Integration
This paper introduces a new approach for generating globally consistent normals for point clouds sampled from manifold surfaces.
Learning Unsigned Distance Fields from Local Shape Functions for 3D Surface Reconstruction
Unsigned distance fields (UDFs) provide a versatile framework for representing a diverse array of 3D shapes, encompassing both watertight and non-watertight geometries.
Towards Secure and Efficient Data Scheduling for Vehicular Social Networks
Efficient data transmission scheduling within vehicular environments poses a significant challenge due to the high mobility of such networks.
GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lighting
The initial SDF represents the coarse geometry of the target object.
DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer
To this end, we propose a novel dual-channel modality fusion network for image-guided point cloud completion(named DMF-Net), in a coarse-to-fine manner.
MIRReS: Multi-bounce Inverse Rendering using Reservoir Sampling
We present MIRReS, a novel two-stage inverse rendering framework that jointly reconstructs and optimizes the explicit geometry, material, and lighting from multi-view images.
The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts
To achieve high usability and dynamic anonymity, ProSan flexibly adjusts its protection targets and strength based on the importance of the words and the privacy leakage risk of the prompts.
RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Rendering
3D Gaussian Splatting (3D-GS) has made a notable advancement in the field of neural rendering, 3D scene reconstruction, and novel view synthesis.
Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction
While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures.
LabObf: A Label Protection Scheme for Vertical Federated Learning Through Label Obfuscation
In this paper, we first propose an embedding extension attack manipulating embeddings to undermine existing defense strategies, which rely on constraining the correlation between the embeddings uploaded by participants and the labels.
Flatten Anything: Unsupervised Neural Surface Parameterization
Surface parameterization plays an essential role in numerous computer graphics and geometry processing applications.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
Large Motion Model for Unified Multi-Modal Motion Generation
In this work, we present Large Motion Model (LMM), a motion-centric, multi-modal framework that unifies mainstream motion generation tasks into a generalist model.
ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds
To the best of our knowledge, this work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
3D Gaussian as a New Era: A Survey
3D Gaussian Splatting (3D-GS) has emerged as a significant advancement in the field of Computer Graphics, offering explicit scene representation and novel view synthesis without the reliance on neural networks, such as Neural Radiance Fields (NeRF).
Topology-Aware Latent Diffusion for 3D Shape Generation
By strategically incorporating topological features into the diffusion process, our generative module is able to produce a richer variety of 3D shapes with different topological structures.
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
The rapid development of open-source large language models (LLMs) has been truly remarkable.
Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network
Point clouds frequently contain noise and outliers presenting obstacles for downstream applications.
Robust Geometry and Reflectance Disentanglement for 3D Face Reconstruction from Sparse-view Images
This paper presents a novel two-stage approach for reconstructing human faces from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual.
Do Not DeepFake Me: Privacy-Preserving Neural 3D Head Reconstruction Without Sensitive Images
While 3D head reconstruction is widely used for modeling, existing neural reconstruction approaches rely on high-resolution multi-view images, posing notable privacy issues.
Dynamic Link Prediction for New Nodes in Temporal Graph Networks
To overcome the few-shot challenge, we incorporate the encoder-predictor into the meta-learning paradigm, which can learn two types of implicit information during the formation of the temporal network through span adaptation and node adaptation.
Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering
The advancements in neural rendering have increased the need for techniques that enable intuitive editing of 3D objects represented as neural implicit surfaces.
Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Covering
We show that the computed iso-surface is the boundary of the $r$-offset volume of the target zero level-set $S$, which is an orientable manifold, regardless of the topology of $S$.
O$^2$-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model
In this paper, we propose a novel framework, empowered by a 2D diffusion-based in-painting model, to reconstruct complete surfaces for the hidden parts of objects.
RePaint-NeRF: NeRF Editting via Semantic Masks and Diffusion Models
The emergence of Neural Radiance Fields (NeRF) has promoted the development of synthesized high-fidelity views of the intricate real world.
NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
To bridge this gap, this paper presents the first attempt to represent geodesics on 3D mesh models using neural implicit functions.
GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation
Local Transformer uses a dynamic graph to calculate all neighboring point weights by intra-domain cross-attention with dynamically updated graph relations, so that every neighboring point could affect the features of centroid with different weights; Global Transformer enlarges the receptive field of Local Transformer by a global self-attention.
Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey
Finally, we share our thoughts on some of the challenges and potential issues that future research in self-supervised learning for pre-training 3D point clouds may encounter.
IterativePFN: True Iterative Point Cloud Filtering
Consequently, a fundamental 3D vision task is the removal of noise, known as point cloud filtering or denoising.
2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images
Yet, a central challenge in UDF-based volume rendering is formulating a proper way to convert unsigned distance values into volume density, ensuring that the resulting weight function remains unbiased and sensitive to occlusions.
Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings
To address this, we propose geometry decomposition and adopt a two-stage, coarse-to-fine training strategy, allowing for progressively capturing high-frequency geometric details.
OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution
Motivated by position encoding, we propose orthogonal position encoding (OPE) - an extension of position encoding - and an OPE-Upscale module to replace the INR-based upsampling module for arbitrary-scale image super-resolution.
Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis
In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels.
GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation
We present a learning-based method, namely GeoUDF, to tackle the long-standing and challenging problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation that explicitly formulates the unsigned distance of a query point as the learnable affine averaging of its distances to the tangent planes of neighboring points on the surface.
PCDNF: Revisiting Learning-based Point Cloud Denoising via Joint Normal Filtering
Motivated by the essential interplay between point cloud denoising and normal filtering, we revisit point cloud denoising from a multitask perspective, and propose an end-to-end network, named PCDNF, to denoise point clouds via joint normal filtering.
RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation
Nevertheless, the correlations between knowledge implied in the multi-turn context and the transition regularities between relations in KGs are under-explored.
Hierarchical Vectorization for Portrait Images
We evaluate our method on the FFHQR dataset and show that our method is effective for common portrait editing tasks, such as retouching, light editing, color transfer and expression editing.
Flexible Portrait Image Editing with Fine-Grained Control
We develop a new method for portrait image editing, which supports fine-grained editing of geometries, colors, lights and shadows using a single neural network model.
IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment
This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation.
Multi-Person Passive WiFi Indoor Localization with Intelligent Reflecting Surface
The past years have witnessed increasing research interest in achieving passive human localization with commodity WiFi devices.
High-Resolution WiFi Imaging with Reconfigurable Intelligent Surfaces
Thus, in this paper, we propose a RIS-aided WiFi imaging framework to achieve high-resolution imaging with the off-the-shelf WiFi devices.
Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Clouds
Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MPVConv improves the accuracy of the backbone (PointNet) by up to \textbf{36\%}, and achieves higher accuracy than the voxel-based model with up to \textbf{34}$\times$ speedups.
PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows
Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets.
Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning
Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MVPConv improves the accuracy of the backbone (PointNet) by up to 36%, and achieves higher accuracy than the voxel-based model with up to 34 times speedup.
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence.
Ranked #6 on
3D Dense Shape Correspondence
on SHREC'19
(using extra training data)
ParaNet: Deep Regular Representation for 3D Point Clouds
Although convolutional neural networks have achieved remarkable success in analyzing 2D images/videos, it is still non-trivial to apply the well-developed 2D techniques in regular domains to the irregular 3D point cloud data.
Deep Magnification-Flexible Upsampling over 3D Point Clouds
In addition, we propose a simple yet effective training strategy to drive such a flexible ability.
Deep Patch-based Human Segmentation
3D human segmentation has seen noticeable progress in re-cent years.
MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling
This paper explores the problem of task-oriented downsampling over 3D point clouds, which aims to downsample a point cloud while maintaining the performance of subsequent applications applied to the downsampled sparse points as much as possible.
STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image
3D reconstruction from a single view image is a long-standing prob-lem in computer vision.
PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling
Matrix $\mathbf T$ approximates the augmented Jacobian matrix of a local parameterization and builds a one-to-one correspondence between the 2D parametric domain and the 3D tangent plane so that we can lift the adaptively distributed 2D samples (which are also learned from data) to 3D space.
Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling
In this paper, we propose a novel deep learning approach that automatically and robustly filters point clouds with removing noise and preserving sharp features and geometric details.
Graphics
Spotting Macro- and Micro-expression Intervals in Long Video Sequences
Both macro- and micro-expression intervals in CAS(ME)$^2$ and SAMM Long Videos are spotted by employing the method of Main Directional Maximal Difference Analysis (MDMD).
HLO: Half-kernel Laplacian Operator for Surface Smoothing
This paper presents a simple yet effective method for feature-preserving surface smoothing.
Computational Geometry Graphics
Blur Removal via Blurred-Noisy Image Pair
Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images.
Parallel and Scalable Heat Methods for Geodesic Distance Computation
In this paper, we propose a parallel and scalable approach for geodesic distance computation on triangle meshes.
Graphics
Manifold SLIC: A Fast Method to Compute Content-Sensitive Superpixels
Superpixels are perceptually meaningful atomic regions that can effectively capture image features.
