Search Results for author: Kejie Li

Found 18 papers, 9 papers with code

Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models

no code implementations4 Oct 2023 Jianglong Ye, Peng Wang, Kejie Li, Yichun Shi, Heng Wang

Specifically, we decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions.

Image to 3D Novel View Synthesis

MVDream: Multi-view Diffusion for 3D Generation

2 code implementations31 Aug 2023 Yichun Shi, Peng Wang, Jianglong Ye, Mai Long, Kejie Li, Xiao Yang

We introduce MVDream, a multi-view diffusion model that is able to generate consistent multi-view images from a given text prompt.

ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces

1 code implementation ICCV 2023 Qianyi Wu, Kaisiyuan Wang, Kejie Li, Jianmin Zheng, Jianfei Cai

Unlike traditional multi-view stereo approaches, the neural implicit surface-based methods leverage neural networks to represent 3D scenes as signed distance functions (SDFs).

3D Reconstruction Multi-View 3D Reconstruction +2

Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach

no code implementations27 Jul 2023 Sandika Biswas, Kejie Li, Biplab Banerjee, Subhasis Chaudhuri, Hamid Rezatofighi

This paper proposes using an implicit feature representation of the scene elements to distinguish a physically plausible alignment of humans and objects from an implausible one.

3D Reconstruction Robot Navigation

Contextualising Implicit Representations for Semantic Tasks

no code implementations22 May 2023 Theo W. Costain, Kejie Li, Victor A. Prisacariu

Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks.

Segmentation Semantic Segmentation

Refinement for Absolute Pose Regression with Neural Feature Synthesis

no code implementations17 Mar 2023 Shuai Chen, Yash Bhalgat, Xinghui Li, Jiawang Bian, Kejie Li, ZiRui Wang, Victor Adrian Prisacariu

Our approach encodes 3D geometric features during training and renders dense novel view features at test time to refine estimated camera poses from arbitrary APR methods.

regression Test

MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices

1 code implementation CVPR 2023 Kejie Li, Jia-Wang Bian, Robert Castle, Philip H. S. Torr, Victor Adrian Prisacariu

The distinct data modality offered by high-resolution RGB images and low-resolution depth maps captured on a mobile device, when combined with precise 3D geometry annotations, presents a unique opportunity for future research on high-fidelity 3D reconstruction.

3D Object Reconstruction 3D Reconstruction

NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior

1 code implementation CVPR 2023 Wenjing Bian, ZiRui Wang, Kejie Li, Jia-Wang Bian, Victor Adrian Prisacariu

Recent advances in this direction demonstrate the possibility of jointly optimising a NeRF and camera poses in forward-facing scenes.

Pose Estimation

Object-Compositional Neural Implicit Surfaces

1 code implementation20 Jul 2022 Qianyi Wu, Xian Liu, Yuedong Chen, Kejie Li, Chuanxia Zheng, Jianfei Cai, Jianmin Zheng

This paper proposes a novel framework, ObjectSDF, to build an object-compositional neural implicit representation with high fidelity in 3D reconstruction and object representation.

3D Reconstruction Novel View Synthesis

ODAM: Object Detection, Association, and Mapping using Posed RGB Video

1 code implementation ICCV 2021 Kejie Li, Daniel DeTone, Steven Chen, Minh Vo, Ian Reid, Hamid Rezatofighi, Chris Sweeney, Julian Straub, Richard Newcombe

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics.

3D Object Detection object-detection +1

Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image

1 code implementation5 Jul 2021 Wenjing Bian, ZiRui Wang, Kejie Li, Victor Adrian Prisacariu

We propose Ray-ONet to reconstruct detailed 3D models from monocular images efficiently.

3D Reconstruction

MOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videos

no code implementations9 Dec 2020 Kejie Li, Hamid Rezatofighi, Ian Reid

Given a new RGB frame, MOLTR firstly applies a monocular 3D detector to localise objects of interest and extract their shape codes that represent the object shapes in a learned embedding space.

Benchmarking Object Localization

FroDO: From Detections to 3D Objects

no code implementations11 May 2020 Kejie Li, Martin Rünz, Meng Tang, Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe

We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers object location, pose and shape in a coarse-to-fine manner.

3D Reconstruction Object Reconstruction +1

Real-Time Monocular Object-Model Aware Sparse SLAM

no code implementations24 Sep 2018 Mehdi Hosseinzadeh, Kejie Li, Yasir Latif, Ian Reid

While sparse point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information.

Camera Localization object-detection +2

Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields

no code implementations ECCV 2018 Kejie Li, Trung Pham, Huangying Zhan, Ian Reid

Given a single image at an arbitrary viewpoint, a CNN predicts multiple surfaces, each in a canonical location relative to the object.

3D Object Reconstruction

Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction

1 code implementation CVPR 2018 Huangying Zhan, Ravi Garg, Chamara Saroj Weerasekera, Kejie Li, Harsh Agarwal, Ian Reid

Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner.

Depth And Camera Motion Depth Prediction +3

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