Search Results for author: Ulrich Neumann

Found 31 papers, 21 papers with code

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

no code implementations19 Mar 2024 Quankai Gao, Qiangeng Xu, Zhe Cao, Ben Mildenhall, Wenchao Ma, Le Chen, Danhang Tang, Ulrich Neumann

While the optimization can draw photometric reference from the input videos or be regulated by generative models, directly supervising Gaussian motions remains underexplored.

Novel View Synthesis Optical Flow Estimation

InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimation

1 code implementation24 Sep 2023 Cho-Ying Wu, Quankai Gao, Chin-Cheng Hsu, Te-Lin Wu, Jing-Wen Chen, Ulrich Neumann

To facilitate our investigation for robustness and address limitations of previous works, we collect InSpaceType, a high-quality and high-resolution RGBD dataset for general indoor environments.

Indoor Monocular Depth Estimation Monocular Depth Estimation

MMVP: Motion-Matrix-based Video Prediction

1 code implementation ICCV 2023 Yiqi Zhong, Luming Liang, Ilya Zharkov, Ulrich Neumann

A central challenge of video prediction lies where the system has to reason the objects' future motions from image frames while simultaneously maintaining the consistency of their appearances across frames.

motion prediction Video Prediction

Strivec: Sparse Tri-Vector Radiance Fields

1 code implementation ICCV 2023 Quankai Gao, Qiangeng Xu, Hao Su, Ulrich Neumann, Zexiang Xu

In contrast to TensoRF which uses a global tensor and focuses on their vector-matrix decomposition, we propose to utilize a cloud of local tensors and apply the classic CANDECOMP/PARAFAC (CP) decomposition to factorize each tensor into triple vectors that express local feature distributions along spatial axes and compactly encode a local neural field.

Tensor Decomposition

Complete 3D Human Reconstruction From a Single Incomplete Image

no code implementations CVPR 2023 Junying Wang, Jae Shin Yoon, Tuanfeng Y. Wang, Krishna Kumar Singh, Ulrich Neumann

This paper presents a method to reconstruct a complete human geometry and texture from an image of a person with only partial body observed, e. g., a torso.

3D Human Reconstruction

Aware of the History: Trajectory Forecasting with the Local Behavior Data

no code implementations20 Jul 2022 Yiqi Zhong, Zhenyang Ni, Siheng Chen, Ulrich Neumann

In this work, we re-introduce this information as a new type of input data for trajectory forecasting systems: the local behavior data, which we conceptualize as a collection of location-specific historical trajectories.

Knowledge Distillation Trajectory Forecasting

Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecasting

no code implementations11 Jul 2022 Bohan Tang, Yiqi Zhong, Chenxin Xu, Wei-Tao Wu, Ulrich Neumann, Yanfeng Wang, Ya zhang, Siheng Chen

Further, we apply the proposed framework to current SOTA multi-agent multi-modal forecasting systems as a plugin module, which enables the SOTA systems to 1) estimate the uncertainty in the multi-agent multi-modal trajectory forecasting task; 2) rank the multiple predictions and select the optimal one based on the estimated uncertainty.

regression Task 2 +1

Point-NeRF: Point-based Neural Radiance Fields

1 code implementation CVPR 2022 Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu, Kalyan Sunkavalli, Ulrich Neumann

Point-NeRF combines the advantages of these two approaches by using neural 3D point clouds, with associated neural features, to model a radiance field.

3D Reconstruction Neural Rendering

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

2 code implementations4 Dec 2021 Qiangeng Xu, Yiqi Zhong, Ulrich Neumann

Finally, the probability of occupancy is also integrated into a proposal refinement module to generate the final bounding boxes.

3D Object Detection Object +2

Collaborative Uncertainty in Multi-Agent Trajectory Forecasting

no code implementations NeurIPS 2021 Bohan Tang, Yiqi Zhong, Ulrich Neumann, Gang Wang, Ya zhang, Siheng Chen

2) The results of trajectory forecasting benchmarks demonstrate that the CU-based framework steadily helps SOTA systems improve their performances.

Trajectory Forecasting

Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices

1 code implementation21 Apr 2021 Cho-Ying Wu, Ke Xu, Chin-Cheng Hsu, Ulrich Neumann

This work focuses on the analysis that whether 3D face models can be learned from only the speech inputs of speakers.

Face Generation Face Model +1

Accurate 3D Facial Geometry Prediction by Multi-Task, Multi-Modal, and Multi-Representation Landmark Refinement Network

1 code implementation16 Apr 2021 Cho-Ying Wu, Qiangeng Xu, Ulrich Neumann

This work focuses on complete 3D facial geometry prediction, including 3D facial alignment via 3D face modeling and face orientation estimation using the proposed multi-task, multi-modal, and multi-representation landmark refinement network (M$^3$-LRN).

3D Face Modelling

Geometry-Aware Instance Segmentation with Disparity Maps

1 code implementation14 Jun 2020 Cho-Ying Wu, Xiaoyan Hu, Michael Happold, Qiangeng Xu, Ulrich Neumann

Mask regression is based on 2D, 2. 5D, and 3D ROI using the pseudo-lidar and image-based representations.

Ranked #16 on Instance Segmentation on Cityscapes val (using extra training data)

Instance Segmentation Semantic Segmentation +1

Scene Completeness-Aware Lidar Depth Completion for Driving Scenario

1 code implementation15 Mar 2020 Cho-Ying Wu, Ulrich Neumann

Recent sparse depth completion for lidars only focuses on the lower scenes and produces irregular estimations on the upper because existing datasets, such as KITTI, do not provide groundtruth for upper areas.

Depth Completion RGBD Semantic Segmentation +4

Grid-GCN for Fast and Scalable Point Cloud Learning

1 code implementation CVPR 2020 Qiangeng Xu, Xudong Sun, Cho-Ying Wu, Panqu Wang, Ulrich Neumann

Compared with popular sampling methods such as Farthest Point Sampling (FPS) and Ball Query, CAGQ achieves up to 50X speed-up.

Point Cloud Classification

Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion

1 code implementation NeurIPS 2019 Yiqi Zhong, Cho-Ying Wu, Suya You, Ulrich Neumann

Such a transformation enables CFCNet to predict features and reconstruct data of missing depth measurements according to their corresponding, transformed RGB features.

Depth Completion

Salient Building Outline Enhancement and Extraction Using Iterative L0 Smoothing and Line Enhancing

1 code implementation6 Jun 2019 Cho-Ying Wu, Ulrich Neumann

Also, we propose to create building masks from semantic segmentation using an encoder-decoder network.

Semantic Segmentation

3DN: 3D Deformation Network

1 code implementation CVPR 2019 Weiyue Wang, Duygu Ceylan, Radomir Mech, Ulrich Neumann

Given such a source 3D model and a target which can be a 2D image, 3D model, or a point cloud acquired as a depth scan, we introduce 3DN, an end-to-end network that deforms the source model to resemble the target.

3D Shape Generation

Efficient Multi-Domain Dictionary Learning with GANs

no code implementations1 Nov 2018 Cho Ying Wu, Ulrich Neumann

In this paper, we propose the multi-domain dictionary learn- ing (MDDL) to make dictionary learning-based classification more robust to data representing in different domains.

Dictionary Learning General Classification +1

Stochastic Dynamics for Video Infilling

no code implementations1 Sep 2018 Qiangeng Xu, Hanwang Zhang, Weiyue Wang, Peter N. Belhumeur, Ulrich Neumann

In this paper, we introduce a stochastic dynamics video infilling (SDVI) framework to generate frames between long intervals in a video.

Depth-aware CNN for RGB-D Segmentation

4 code implementations ECCV 2018 Weiyue Wang, Ulrich Neumann

Convolutional neural networks (CNN) are limited by the lack of capability to handle geometric information due to the fixed grid kernel structure.

Segmentation Semantic Segmentation +1

Learning to Prune Filters in Convolutional Neural Networks

no code implementations23 Jan 2018 Qiangui Huang, Kevin Zhou, Suya You, Ulrich Neumann

Specifically, we introduce a "try-and-learn" algorithm to train pruning agents that remove unnecessary CNN filters in a data-driven way.

Semantic Segmentation

SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

1 code implementation CVPR 2018 Weiyue Wang, Ronald Yu, Qiangui Huang, Ulrich Neumann

Experimental results on various 3D scenes show the effectiveness of our method on 3D instance segmentation, and we also evaluate the capability of SGPN to improve 3D object detection and semantic segmentation results.

3D Instance Segmentation 3D Object Detection +5

Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks

1 code implementation ICCV 2017 Weiyue Wang, Qiangui Huang, Suya You, Chao Yang, Ulrich Neumann

The 3D-ED-GAN is a 3D convolutional neural network trained with a generative adversarial paradigm to fill missing 3D data in low-resolution.

Generative Adversarial Network

Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning

no code implementations22 Nov 2016 Qiangui Huang, Weiyue Wang, Kevin Zhou, Suya You, Ulrich Neumann

A novel neural network architecture is built for scene labeling tasks where one of the variants of the new RNN unit, Gated Recurrent Unit with Explicit Long-range Conditioning (GRU-ELC), is used to model multi scale contextual dependencies in images.

Scene Labeling

Cannot find the paper you are looking for? You can Submit a new open access paper.