75 citations · 414 across the 23 of their papers we have counts for
25 papers
Interactive Segment Anything NeRF with Feature Imitation
Xiaokang Chen, Jiaxiang Tang, Diwen Wan +2
This paper investigates the potential of enhancing Neural Radiance Fields (NeRF) with semantics to expand their applications. Although NeRF has been proven useful in real-world app…
Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Prediction
Xiaokang Chen, Yajie Xing, Gang Zeng
Semantic Scene Completion (SSC) aims to simultaneously predict the volumetric occupancy and semantic category of a 3D scene. In this paper, we propose a real-time semantic scene co…
Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement
Jiaxiang Tang, Hang Zhou, Xiaokang Chen +4
Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in image-based 3D reconstruction. However, their implicit volumetric representations differ significantly f…
Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
Jiaxiang Tang, Kaisiyuan Wang, Hang Zhou +6
While dynamic Neural Radiance Fields (NeRF) have shown success in high-fidelity 3D modeling of talking portraits, the slow training and inference speed severely obstruct their pote…
DETR: Decoder Distillation for Detection Transformer
Xiaokang Chen, Jiahui Chen, Yan Liu +1
While various knowledge distillation (KD) methods in CNN-based detectors show their effectiveness in improving small students, the baselines and recipes for DETR-based detectors ar…
JVLDLoc: a Joint Optimization of Visual-LiDAR Constraints and Direction Priors for Localization in Driving Scenario
Longrui Dong, Gang Zeng
The ability for a moving agent to localize itself in environment is the basic demand for emerging applications, such as autonomous driving, etc. Many existing methods based on mult…
Conditional DETR V2: Efficient Detection Transformer with Box Queries
Xiaokang Chen, Fangyun Wei, Gang Zeng +1
In this paper, we are interested in Detection Transformer (DETR), an end-to-end object detection approach based on a transformer encoder-decoder architecture without hand-crafted p…
Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
Qiang Chen, Xiaokang Chen, Jian Wang +7
Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing. It is known…
Compressible-composable NeRF via Rank-residual Decomposition
Jiaxiang Tang, Xiaokang Chen, Jingbo Wang +1
Neural Radiance Field (NeRF) has emerged as a compelling method to represent 3D objects and scenes for photo-realistic rendering. However, its implicit representation causes diffic…
MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation
Min Zhong, Xinghao Chen, Xiaokang Chen +2
This paper studies the 3D instance segmentation problem, which has a variety of real-world applications such as robotics and augmented reality. Since the surroundings of 3D objects…
Point Scene Understanding via Disentangled Instance Mesh Reconstruction
Jiaxiang Tang, Xiaokang Chen, Jingbo Wang +1
Semantic scene reconstruction from point cloud is an essential and challenging task for 3D scene understanding. This task requires not only to recognize each instance in the scene,…
Context Autoencoder for Self-Supervised Representation Learning
Xiaokang Chen, Mingyu Ding, Xiaodi Wang +7
We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in…
Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective
Xiaokang Chen, Jiaxiang Tang, Jingbo Wang +1
We revisit Semantic Scene Completion (SSC), a useful task to predict the semantic and occupancy representation of 3D scenes, in this paper. A number of methods for this task are al…
Conditional DETR for Fast Training Convergence
Depu Meng, Xiaokang Chen, Zejia Fan +5
The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the c…
Joint Implicit Image Function for Guided Depth Super-Resolution
Jiaxiang Tang, Xiaokang Chen, Gang Zeng
Guided depth super-resolution is a practical task where a low-resolution and noisy input depth map is restored to a high-resolution version, with the help of a high-resolution RGB…
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
Xiaokang Chen, Yuhui Yuan, Gang Zeng +1
In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization ap…
Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing
Yajie Xing, Jingbo Wang, Gang Zeng
Depth data provide geometric information that can bring progress in RGB-D scene parsing tasks. Several recent works propose RGB-D convolution operators that construct receptive fie…
Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
Xiaokang Chen, Kwan-Yee Lin, Jingbo Wang +4
Depth information has proven to be a useful cue in the semantic segmentation of RGB-D images for providing a geometric counterpart to the RGB representation. Most existing works si…
3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
Xiaokang Chen, Kwan-Yee Lin, Chen Qian +2
The goal of the Semantic Scene Completion (SSC) task is to simultaneously predict a completed 3D voxel representation of volumetric occupancy and semantic labels of objects in the…
Meta Networks for Neural Style Transfer
Falong Shen, Shuicheng Yan, Gang Zeng
In this paper we propose a new method to get the specified network parameters through one time feed-forward propagation of the meta networks and explore the application to neural s…
Weighted Residuals for Very Deep Networks
Falong Shen, Gang Zeng
Deep residual networks have recently shown appealing performance on many challenging computer vision tasks. However, the original residual structure still has some defects making i…
Fast Semantic Image Segmentation with High Order Context and Guided Filtering
Falong Shen, Gang Zeng
This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order c…
Fast Neighborhood Graph Search using Cartesian Concatenation
Jingdong Wang, Jing Wang, Gang Zeng +3
In this paper, we propose a new data structure for approximate nearest neighbor search. This structure augments the neighborhood graph with a bridge graph. We propose to exploit Ca…
Fast Approximate -Means via Cluster Closures
Jingdong Wang, Jing Wang, Qifa Ke +2
-means, a simple and effective clustering algorithm, is one of the most widely used algorithms in multimedia and computer vision community. Traditional -means is an iterative…