Search Results for author:
Found 15 papers, 9 papers with code
Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds
We study how choices of input point cloud coordinate frames impact learning of manipulation skills from 3D point clouds.
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation
The reason is that the learnt weights for balancing the importance between the shape and base components in ShapeConv become constants in the inference phase, and thus can be fused into the following convolution, resulting in a network that is identical to one with vanilla convolutional layers.
Ranked #3 on
Semantic Segmentation
on Stanford2D3D - RGBD
DO-Conv: Depthwise Over-parameterized Convolutional Layer
Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization.
GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling
Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation.
Face Identity Disentanglement via Latent Space Mapping
Learning disentangled representations of data is a fundamental problem in artificial intelligence.
MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion
To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone.
PointCNN: Convolution On X-Transformed Points
We present a simple and general framework for feature learning from point cloud.
Ranked #5 on
3D Semantic Segmentation
on DALES
DiDA: Disentangled Synthesis for Domain Adaptation
The key idea is that by learning to separately extract both the common and the domain-specific features, one can synthesize more target domain data with supervision, thereby boosting the domain adaptation performance.
PointCNN: Convolution On $\mathcal{X}$-Transformed Points
The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN.
Ranked #1 on
3D Instance Segmentation
on S3DIS
(mIoU metric)
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
Bundle Optimization for Multi-aspect Embedding
Understanding semantic similarity among images is the core of a wide range of computer vision applications.
A Holistic Approach for Data-Driven Object Cutout
We show that the resulting P-maps may be used to evaluate how likely a rectangle proposal is to contain an instance of the class, and further process good proposals to produce an accurate object cutout mask.
FPNN: Field Probing Neural Networks for 3D Data
Each field probing filter is a set of probing points --- sensors that perceive the space.
Ranked #5 on
3D Object Recognition
on ModelNet40
Synthesizing Training Images for Boosting Human 3D Pose Estimation
Human 3D pose estimation from a single image is a challenging task with numerous applications.
Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
Object viewpoint estimation from 2D images is an essential task in computer vision.
