OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning

no code implementations • 20 Nov 2023 • Haiyang Ying, Yixuan Yin, Jinzhi Zhang, Fan Wang, Tao Yu, Ruqi Huang, Lu Fang

Towards holistic understanding of 3D scenes, a general 3D segmentation method is needed that can segment diverse objects without restrictions on object quantity or categories, while also reflecting the inherent hierarchical structure.

Contrastive Learning Segmentation

Spatially and Spectrally Consistent Deep Functional Maps

1 code implementation • ICCV 2023 • Mingze Sun, Shiwei Mao, Puhua Jiang, Maks Ovsjanikov, Ruqi Huang

We first justify that under certain conditions, the learned maps, when represented in the spectral domain, are already cycle consistent.

Neural Intrinsic Embedding for Non-rigid Point Cloud Matching

no code implementations • CVPR 2023 • Puhua Jiang, Mingze Sun, Ruqi Huang

As a primitive 3D data representation, point clouds are prevailing in 3D sensing, yet short of intrinsic structural information of the underlying objects.

Point Cloud Registration Weakly-supervised Learning

RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation

no code implementations • ICCV 2023 • Haozhe Lin, Zequn Chen, Jinzhi Zhang, Bing Bai, Yu Wang, Ruqi Huang, Lu Fang

The CGG task capitalizes on the calibrated multiview videos of a dynamic scene, and targets at recovering semantic information (coordination, trajectories and relationships) of the presented objects in the form of spatio-temporal context graph in 4D space.

Graph Generation Scene Understanding

Optical Neural Ordinary Differential Equations

no code implementations • 26 Sep 2022 • Yun Zhao, Hang Chen, Min Lin, Haiou Zhang, Tao Yan, Xing Lin, Ruqi Huang, Qionghai Dai

Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance.

Image Classification Trajectory Prediction

Cross-Camera Deep Colorization

1 code implementation • 26 Aug 2022 • Yaping Zhao, Haitian Zheng, Mengqi Ji, Ruqi Huang

Our method takes cross-domain and cross-scale images as input, and consequently synthesizes HR colorization results to facilitate the trade-off between spatial-temporal resolution and color depth in the single-camera imaging system.

Colorization

EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

1 code implementation • 15 Oct 2021 • Yaping Zhao, Mengqi Ji, Ruqi Huang, Bin Wang, Shengjin Wang

In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i. e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence.

Reference-based Video Super-Resolution Video Super-Resolution

OperatorNet: Recovering 3D Shapes From Difference Operators

1 code implementation • ICCV 2019 • Ruqi Huang, Marie-Julie Rakotosaona, Panos Achlioptas, Leonidas Guibas, Maks Ovsjanikov

This paper proposes a learning-based framework for reconstructing 3D shapes from functional operators, compactly encoded as small-sized matrices.