321 citations · 555 across the 36 of their papers we have counts for
33 papers · 1 filter
HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving
Hongyu Zhou, Longzhong Lin, Jiabao Wang +6
In the past few decades, autonomous driving algorithms have made significant progress in perception, planning, and control. However, evaluating individual components does not fully…
Efficient Depth-Guided Urban View Synthesis
Sheng Miao, Jiaxin Huang, Dongfeng Bai +4
Recent advances in implicit scene representation enable high-fidelity street view novel view synthesis. However, existing methods optimize a neural radiance field for each scene, r…
PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction
Xuan Yu, Yili Liu, Chenrui Han +5
Panoptic reconstruction is a challenging task in 3D scene understanding. However, most existing methods heavily rely on pre-trained semantic segmentation models and known 3D object…
Learning Temporally Consistent Video Depth from Video Diffusion Priors
Jiahao Shao, Yuanbo Yang, Hongyu Zhou +6
This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharin…
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation
Sicheng Li, Hao Li, Yiyi Liao +1
The emergence of Neural Radiance Fields (NeRF) has greatly impacted 3D scene modeling and novel-view synthesis. As a kind of visual media for 3D scene representation, compression w…
Learning 3D-Aware GANs from Unposed Images with Template Feature Field
Xinya Chen, Hanlei Guo, Yanrui Bin +5
Collecting accurate camera poses of training images has been shown to well serve the learning of 3D-aware generative adversarial networks (GANs) yet can be quite expensive in pract…
HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting
Hongyu Zhou, Jiahao Shao, Lu Xu +6
Holistic understanding of urban scenes based on RGB images is a challenging yet important problem. It encompasses understanding both the geometry and appearance to enable novel vie…
REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices
Chaojie Ji, Yufeng Li, Yiyi Liao
This work tackles the challenging task of achieving real-time novel view synthesis for reflective surfaces across various scenes. Existing real-time rendering methods, especially t…
Recent Trends in 3D Reconstruction of General Non-Rigid Scenes
Raza Yunus, Jan Eric Lenssen, Michael Niemeyer +7
Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthe…
DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Features
Jun Wu, Sicheng Li, Sihui Ji +4
Recovering 3D geometry and textures of individual objects is crucial for many robotics applications, such as manipulation, pose estimation, and autonomous driving. However, decompo…
VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis
Xinya Chen, Jiaxin Huang, Yanrui Bin +2
Unsupervised learning of 3D-aware generative adversarial networks has lately made much progress. Some recent work demonstrates promising results of learning human generative models…
PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes
Xiao Fu, Shangzhan Zhang, Tianrun Chen +4
Training perception systems for self-driving cars requires substantial 2D annotations that are labor-intensive to manual label. While existing datasets provide rich annotations on…
MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving
Zirui Wu, Tianyu Liu, Liyi Luo +13
Nowadays, autonomous cars can drive smoothly in ordinary cases, and it is widely recognized that realistic sensor simulation will play a critical role in solving remaining corner c…
UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields
Yuanbo Yang, Yifei Yang, Hanlei Guo +3
Generating photorealistic images with controllable camera pose and scene contents is essential for many applications including AR/VR and simulation. Despite the fact that rapid pro…
RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction
Zizhang Li, Xiaoyang Lyu, Yuanyuan Ding +3
Recently, neural implicit surfaces have become popular for multi-view reconstruction. To facilitate practical applications like scene editing and manipulation, some works extend th…
Painting 3D Nature in 2D: View Synthesis of Natural Scenes from a Single Semantic Mask
Shangzan Zhang, Sida Peng, Tianrun Chen +5
We introduce a novel approach that takes a single semantic mask as input to synthesize multi-view consistent color images of natural scenes, trained with a collection of single ima…
Learning 3D-aware Image Synthesis with Unknown Pose Distribution
Zifan Shi, Yujun Shen, Yinghao Xu +5
Existing methods for 3D-aware image synthesis largely depend on the 3D pose distribution pre-estimated on the training set. An inaccurate estimation may mislead the model into lear…
SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory
Sicheng Li, Hao Li, Yue Wang +2
Neural Radiance Fields (NeRF) have demonstrated superior novel view synthesis performance but are slow at rendering. To speed up the volume rendering process, many acceleration met…
Deep Generative Models on 3D Representations: A Survey
Zifan Shi, Sida Peng, Yinghao Xu +3
Generative models aim to learn the distribution of observed data by generating new instances. With the advent of neural networks, deep generative models, including variational auto…
DPCN++: Differentiable Phase Correlation Network for Versatile Pose Registration
Zexi Chen, Yiyi Liao, Haozhe Du +5
Pose registration is critical in vision and robotics. This paper focuses on the challenging task of initialization-free pose registration up to 7DoF for homogeneous and heterogeneo…
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
Katja Schwarz, Axel Sauer, Michael Niemeyer +2
State-of-the-art 3D-aware generative models rely on coordinate-based MLPs to parameterize 3D radiance fields. While demonstrating impressive results, querying an MLP for every samp…
Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation
Xiao Fu, Shangzhan Zhang, Tianrun Chen +5
Large-scale training data with high-quality annotations is critical for training semantic and instance segmentation models. Unfortunately, pixel-wise annotation is labor-intensive…
A Visual Navigation Perspective for Category-Level Object Pose Estimation
Jiaxin Guo, Fangxun Zhong, Rong Xiong +3
This paper studies category-level object pose estimation based on a single monocular image. Recent advances in pose-aware generative models have paved the way for addressing this c…
On the Frequency Bias of Generative Models
Katja Schwarz, Yiyi Liao, Andreas Geiger
The key objective of Generative Adversarial Networks (GANs) is to generate new data with the same statistics as the provided training data. However, multiple recent works show that…