Existing shadow detection datasets often contain missing or mislabeled
s...
We introduce a new diffusion-based approach for shape completion on 3D r...
We present the UrbanBIS benchmark for large-scale 3D urban understanding...
3D scene understanding, e.g., point cloud semantic and instance segmenta...
This paper presents a new approach for 3D shape generation, inversion, a...
LiDAR-produced point clouds are the major source for most state-of-the-a...
Video instance shadow detection aims to simultaneously detect, segment,
...
This paper presents a new approach for 3D shape generation, enabling dir...
Text-guided 3D shape generation remains challenging due to the absence o...
This paper formulates a new problem, instance shadow detection, which ai...
Despite the quality improvement brought by the recent methods, video
sup...
To boost a detector for single-frame 3D object detection, we present a n...
This paper presents a new approach to boost a single-modality (LiDAR) 3D...
Reconstructing 3D geometry from unoriented point clouds can benefit
many...
This paper introduces a novel framework called DTNet for 3D mesh
reconst...
In this work, we explore the challenging task of generating 3D shapes fr...
Industrial bin picking is a challenging task that requires accurate and
...
This work presents an innovative method for point set self-embedding, th...
We present a novel two-stage approach for automated floorplan design in
...
Rapid progress in 3D semantic segmentation is inseparable from the advan...
3D hand-mesh reconstruction from RGB images facilitates many application...
We present SP-GAN, a new unsupervised sphere-guided generative model for...
The ability to recognize the position and order of the floor-level lines...
Point clouds produced by 3D scanning are often sparse, non-uniform, and
...
We present Self-Ensembling Single-Stage object Detector (SE-SSD) for acc...
Point cloud semantic segmentation often requires largescale annotated
tr...
Indoor scene semantic parsing from RGB images is very challenging due to...
This work presents a new approach based on deep learning to automaticall...
Existing single-stage detectors for locating objects in point clouds oft...
Deep convolutional neural networks have significantly boosted the perfor...
This paper presents the idea ofmono-nizingbinocular videos and a frame-w...
The generalization capability of neural networks across domains is cruci...
This paper presents a deep normal filtering network, called DNF-Net, for...
Instance segmentation is an important task for scene understanding. Comp...
Recently, many deep neural networks were designed to process 3D point cl...
This paper presents a novel non-local part-aware deep neural network to
...
We present PointAugment, a new auto-augmentation framework that automati...
Existing augmented reality (AR) applications often ignore occlusion betw...
Instance shadow detection is a brand new problem, aiming to find shadow
...
Shadow detection in general photos is a nontrivial problem, due to the
c...
Diabetic retinopathy (DR) and diabetic macular edema (DME) are the leadi...
We achieve 3D semantic scene labeling by exploring semantic relation bet...
This paper presents a new approach to recognize elements in floor plan
l...
Selection is a fundamental task in exploratory analysis and visualizatio...
Point clouds acquired from range scans are often sparse, noisy, and
non-...
Training deep convolutional neural networks usually requires a large amo...
Surgical tool presence detection and surgical phase recognition are two
...
The goal of few-shot learning is to recognize new visual concepts with j...
Rare diseases have extremely low-data regimes, unlike common diseases wi...
Accurate segmentation of the optic disc (OD) and cup (OC)in fundus image...