70 citations · 254 across the 24 of their papers we have counts for
24 papers
PanoContext-Former: Panoramic Total Scene Understanding with a Transformer
Yuan Dong, Chuan Fang, Liefeng Bo +2
Panoramic image enables deeper understanding and more holistic perception of surrounding environment, which can naturally encode enriched scene context information comp…
Compact Real-time Radiance Fields with Neural Codebook
Lingzhi Li, Zhongshu Wang, Zhen Shen +2
Reconstructing neural radiance fields with explicit volumetric representations, demonstrated by Plenoxels, has shown remarkable advantages on training and rendering efficiency, whi…
Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos
Ziqian Bai, Feitong Tan, Zeng Huang +12
We propose a method to learn a high-quality implicit 3D head avatar from a monocular RGB video captured in the wild. The learnt avatar is driven by a parametric face model to achie…
Learning Optical Flow from Event Camera with Rendered Dataset
Xinglong Luo, Kunming Luo, Ao Luo +3
We study the problem of estimating optical flow from event cameras. One important issue is how to build a high-quality event-flow dataset with accurate event values and flow labels…
Dense RGB SLAM with Neural Implicit Maps
Heng Li, Xiaodong Gu, Weihao Yuan +3
There is an emerging trend of using neural implicit functions for map representation in Simultaneous Localization and Mapping (SLAM). Some pioneer works have achieved encouraging r…
RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging
Heng Li, Zhaopeng Cui, Shuaicheng Liu +1
This paper proposes a deep recurrent Rotation Averaging Graph Optimizer (RAGO) for Multiple Rotation Averaging (MRA). Conventional optimization-based methods usually fail to produc…
Streaming Radiance Fields for 3D Video Synthesis
Lingzhi Li, Zhen Shen, Zhongshu Wang +2
We present an explicit-grid based method for efficiently reconstructing streaming radiance fields for novel view synthesis of real world dynamic scenes. Instead of training a singl…
DART: Articulated Hand Model with Diverse Accessories and Rich Textures
Daiheng Gao, Yuliang Xiu, Kailin Li +6
Hand, the bearer of human productivity and intelligence, is receiving much attention due to the recent fever of digital twins. Among different hand morphable models, MANO has been…
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
Qiyu Dai, Jiyao Zhang, Qiwei Li +5
Commercial depth sensors usually generate noisy and missing depths, especially on specular and transparent objects, which poses critical issues to downstream depth or point cloud-b…
RenderNet: Visual Relocalization Using Virtual Viewpoints in Large-Scale Indoor Environments
Jiahui Zhang, Shitao Tang, Kejie Qiu +6
Visual relocalization has been a widely discussed problem in 3D vision: given a pre-constructed 3D visual map, the 6 DoF (Degrees-of-Freedom) pose of a query image is estimated. Re…
Unseen Object 6D Pose Estimation: A Benchmark and Baselines
Minghao Gou, Haolin Pan, Hao-Shu Fang +3
Estimating the 6D pose for unseen objects is in great demand for many real-world applications. However, current state-of-the-art pose estimation methods can only handle objects tha…
Text/Speech-Driven Full-Body Animation
Wenlin Zhuang, Jinwei Qi, Peng Zhang +2
Due to the increasing demand in films and games, synthesizing 3D avatar animation has attracted much attention recently. In this work, we present a production-ready text/speech-dri…
RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds
Xiaodong Gu, Chengzhou Tang, Weihao Yuan +3
3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Inspired by 2D flow estimation, recent methods employ deep neural networks to…
Efficient Virtual View Selection for 3D Hand Pose Estimation
Jian Cheng, Yanguang Wan, Dexin Zuo +6
3D hand pose estimation from single depth is a fundamental problem in computer vision, and has wide applications.However, the existing methods still can not achieve satisfactory ha…
AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling
Ziqian Bai, Timur Bagautdinov, Javier Romero +3
Neural fields such as implicit surfaces have recently enabled avatar modeling from raw scans without explicit temporal correspondences. In this work, we exploit autoregressive mode…
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation
Weihao Yuan, Xiaodong Gu, Zuozhuo Dai +2
Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful net…
GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings
Zhaohua Zheng, Jianfang Li, Lingjie Zhu +3
Spotting graphical symbols from the computer-aided design (CAD) drawings is essential to many industrial applications. Different from raster images, CAD drawings are vector graphic…
QuadTree Attention for Vision Transformers
Shitao Tang, Jiahui Zhang, Siyu Zhu +1
Transformers have been successful in many vision tasks, thanks to their capability of capturing long-range dependency. However, their quadratic computational complexity poses a maj…
GB-CosFace: Rethinking Softmax-based Face Recognition from the Perspective of Open Set Classification
Lizhe Liu, Mingqiang Chen, Xiaohao Chen +2
State-of-the-art face recognition methods typically take the multi-classification pipeline and adopt the softmax-based loss for optimization. Although these methods have achieved g…
FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting
Zhiwen Fan, Lingjie Zhu, Honghua Li +3
Access to large and diverse computer-aided design (CAD) drawings is critical for developing symbol spotting algorithms. In this paper, we present FloorPlanCAD, a large-scale real-w…
CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
Lizhe Liu, Xiaohao Chen, Siyu Zhu +1
Modern deep-learning-based lane detection methods are successful in most scenarios but struggling for lane lines with complex topologies. In this work, we propose CondLaneNet, a no…
OCRTOC: A Cloud-Based Competition and Benchmark for Robotic Grasping and Manipulation
Ziyuan Liu, Wei Liu, Yuzhe Qin +8
In this paper, we propose a cloud-based benchmark for robotic grasping and manipulation, called the OCRTOC benchmark. The benchmark focuses on the object rearrangement problem, spe…
DRO: Deep Recurrent Optimizer for Video to Depth
Xiaodong Gu, Weihao Yuan, Zuozhuo Dai +4
There are increasing interests of studying the video-to-depth (V2D) problem with machine learning techniques. While earlier methods directly learn a mapping from images to depth ma…
Batch DropBlock Network for Person Re-identification and Beyond
Zuozhuo Dai, Mingqiang Chen, Xiaodong Gu +2
Since the person re-identification task often suffers from the problem of pose changes and occlusions, some attentive local features are often suppressed when training CNNs. In thi…