418 citations · 811 across the 14 of their papers we have counts for
14 papers
TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks
Jinjie Mai, Wenxuan Zhu, Sara Rojas +6
Neural radiance fields (NeRFs) generally require many images with accurate poses for accurate novel view synthesis, which does not reflect realistic setups where views can be spars…
GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
Abdullah Hamdi, Luke Melas-Kyriazi, Jinjie Mai +5
Advancements in 3D Gaussian Splatting have significantly accelerated 3D reconstruction and generation. However, it may require a large number of Gaussians, which creates a substant…
DrNet: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
Chen Zhao, Shuming Liu, Karttikeya Mangalam +5
Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning, which is highly memo…
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Guocheng Qian, Jinjie Mai, Abdullah Hamdi +8
We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the…
Exploring Open-Vocabulary Semantic Segmentation without Human Labels
Jun Chen, Deyao Zhu, Guocheng Qian +6
Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level. However, existing approaches oft…
LLM as A Robotic Brain: Unifying Egocentric Memory and Control
Jinjie Mai, Jun Chen, Bing Li +3
Embodied AI focuses on the study and development of intelligent systems that possess a physical or virtual embodiment (i.e. robots) and are able to dynamically interact with their…
Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding
Guocheng Qian, Abdullah Hamdi, Xingdi Zhang +1
While Transformers have achieved impressive success in natural language processing and computer vision, their performance on 3D point clouds is relatively poor. This is mainly due…
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
Guocheng Qian, Yuchen Li, Houwen Peng +4
PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks such…
When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
Guocheng Qian, Xuanyang Zhang, Guohao Li +5
The key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which i…
ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning
Guocheng Qian, Hasan Abed Al Kader Hammoud, Guohao Li +2
Access to 3D point cloud representations has been widely facilitated by LiDAR sensors embedded in various mobile devices. This has led to an emerging need for fast and accurate poi…
PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks
Guocheng Qian, Abdulellah Abualshour, Guohao Li +2
The effectiveness of learning-based point cloud upsampling pipelines heavily relies on the upsampling modules and feature extractors used therein. For the point upsampling module,…
SGAS: Sequential Greedy Architecture Search
Guohao Li, Guocheng Qian, Itzel C. Delgadillo +3
Architecture design has become a crucial component of successful deep learning. Recent progress in automatic neural architecture search (NAS) shows a lot of promise. However, disco…
DeepGCNs: Making GCNs Go as Deep as CNNs
Guohao Li, Matthias Müller, Guocheng Qian +4
Convolutional Neural Networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, act…
Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline
Guocheng Qian, Yuanhao Wang, Jinjin Gu +4
Imaging is usually a mixture problem of incomplete color sampling, noise degradation, and limited resolution. This mixture problem is typically solved by a sequential solution that…