110 citations · 925 across the 79 of their papers we have counts for
17 papers · 2 filters
Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing
Jingsen Zhu, Fujun Luan, Yuchi Huo +7
Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-…
Improving Feature-based Visual Localization by Geometry-Aided Matching
Hailin Yu, Youji Feng, Weicai Ye +3
Feature matching is crucial in visual localization, where 2D-3D correspondence plays a major role in determining the accuracy of camera pose. A sufficient number of well-distribute…
IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis
Weicai Ye, Shuo Chen, Chong Bao +4
Existing inverse rendering combined with neural rendering methods can only perform editable novel view synthesis on object-specific scenes, while we present intrinsic neural radian…
DELTAR: Depth Estimation from a Light-weight ToF Sensor and RGB Image
Yijin Li, Xinyang Liu, Wenqi Dong +5
Light-weight time-of-flight (ToF) depth sensors are small, cheap, low-energy and have been massively deployed on mobile devices for the purposes like autofocus, obstacle detection,…
Vox-Surf: Voxel-based Implicit Surface Representation
Hai Li, Xingrui Yang, Hongjia Zhai +3
Virtual content creation and interaction play an important role in modern 3D applications such as AR and VR. Recovering detailed 3D models from real scenes can significantly expand…
NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing
Bangbang Yang, Chong Bao, Junyi Zeng +4
Very recently neural implicit rendering techniques have been rapidly evolved and shown great advantages in novel view synthesis and 3D scene reconstruction. However, existing neura…
Factorized and Controllable Neural Re-Rendering of Outdoor Scene for Photo Extrapolation
Boming Zhao, Bangbang Yang, Zhenyang Li +6
Expanding an existing tourist photo from a partially captured scene to a full scene is one of the desired experiences for photography applications. Although photo extrapolation has…
DFlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance
Xingyuan Yu, Weicai Ye, Xiyue Guo +5
In this paper, we introduce a self-supervised deep SLAM method that robustly operates in dynamic scenes while accurately identifying dynamic components. Our method leverages a dual…
PVO: Panoptic Visual Odometry
Weicai Ye, Xinyue Lan, Shuo Chen +5
We present PVO, a novel panoptic visual odometry framework to achieve more comprehensive modeling of the scene motion, geometry, and panoptic segmentation information. Our PVO mode…
Neural 3D Scene Reconstruction with the Manhattan-world Assumption
Haoyu Guo, Sida Peng, Haotong Lin +4
This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view images. Many previous works have shown impressive reconstruction results on textured objects,…
Neural Rendering in a Room: Amodal 3D Understanding and Free-Viewpoint Rendering for the Closed Scene Composed of Pre-Captured Objects
Bangbang Yang, Yinda Zhang, Yijin Li +4
We, as human beings, can understand and picture a familiar scene from arbitrary viewpoints given a single image, whereas this is still a grand challenge for computers. We hereby pr…
Normal and Visibility Estimation of Human Face from a Single Image
Fuzhi Zhong, Rui Wang, Yuchi Huo +1
Recent work on the intrinsic image of humans starts to consider the visibility of incident illumination and encodes the light transfer function by spherical harmonics. In this pape…
Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
Jiacong Hu, Jing Gao, Jingwen Ye +4
With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive. In this paper, we start fr…
Hybrid Mesh-neural Representation for 3D Transparent Object Reconstruction
Jiamin Xu, Zihan Zhu, Hujun Bao +1
We propose a novel method to reconstruct the 3D shapes of transparent objects using hand-held captured images under natural light conditions. It combines the advantage of explicit…
Animatable Implicit Neural Representations for Creating Realistic Avatars from Videos
Sida Peng, Zhen Xu, Junting Dong +5
This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene i…
Hybrid Tracker with Pixel and Instance for Video Panoptic Segmentation
Weicai Ye, Xinyue Lan, Ge Su +3
Video Panoptic Segmentation (VPS) aims to generate coherent panoptic segmentation and track the identities of all pixels across video frames. Existing methods predominantly utilize…
SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video
Boyi Jiang, Yang Hong, Hujun Bao +1
We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self…