Related papers: Improving 2D Feature Representations by 3D-Aware F…
We present a novel animatable 3D Gaussian model for rendering high-fidelity free-view human motions in real time. Compared to existing NeRF-based methods, the model owns better capability in synthesizing high-frequency details without the…
The human face constantly conveys information, both consciously and subconsciously. However, as basic as it is for humans to visually interpret this information, it is quite a big challenge for machines. Conventional semantic facial feature…
Recent advances in 3D semantic segmentation with deep neural networks have shown remarkable success, with rapid performance increase on available datasets. However, current 3D semantic segmentation benchmarks contain only a small number of…
Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…
Recent advances in radiance fields and novel view synthesis enable creation of realistic digital twins from photographs. However, current methods struggle with flat, texture-less surfaces, creating uneven and semi-transparent…
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…
Camera-based 3D semantic occupancy prediction offers an efficient and cost-effective solution for perceiving surrounding scenes in autonomous driving. However, existing works rely on explicit occupancy state inference, leading to numerous…
Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing significant challenges…
Despite recent advances in facial recognition, there remains a fundamental issue concerning degradations in performance due to substantial perspective (pose) differences between enrollment and query (probe) imagery. Therefore, we propose a…
Recent advances in 3D datasets and multimodal models have greatly improved natural language 3D scene understanding. However, most 3D referring segmentation methods do not explicitly represent the observer viewpoint, making spatial relations…
Generating images with both photorealism and multiview 3D consistency is crucial for 3D-aware GANs, yet existing methods struggle to achieve them simultaneously. Improving the photorealism via CNN-based 2D super-resolution can break the…
Unsupervised domain adaptation (UDA) is vital for alleviating the workload of labeling 3D point cloud data and mitigating the absence of labels when facing a newly defined domain. Various methods of utilizing images to enhance the…
Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from…
Modeling and understanding the 3D world is crucial for various applications, from augmented reality to robotic navigation. Recent advancements based on 3D Gaussian Splatting have integrated semantic information from multi-view images into…
A multitude of prevalent pre-trained models mark a major milestone in the development of artificial intelligence, while fine-tuning has been a common practice that enables pretrained models to figure prominently in a wide array of target…
Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description. However, existing methods only consider the dependency between the entire sentence and the target…
Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud data. They usually focus on the 3D domain only, without…
As capturing devices become common, 3D scans of interior spaces are acquired on a daily basis. Through scene comparison over time, information about objects in the scene and their changes is inferred. This information is important for…
Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that…
3D semantic segmentation on multi-scan large-scale point clouds plays an important role in autonomous systems. Unlike the single-scan-based semantic segmentation task, this task requires distinguishing the motion states of points in…