Erqun Dong
YOU?
Author Swipe
View article: ROODI: Reconstructing Occluded Objects with Denoising Inpainters
ROODI: Reconstructing Occluded Objects with Denoising Inpainters Open
While the quality of novel-view images has improved dramatically with 3D Gaussian Splatting, extracting specific objects from scenes remains challenging. Isolating individual 3D Gaussian primitives for each object and handling occlusions i…
View article: ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models
ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models Open
Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent…
View article: Differentiable SLAM Helps Deep Learning-based LiDAR Perception Tasks
Differentiable SLAM Helps Deep Learning-based LiDAR Perception Tasks Open
We investigate a new paradigm that uses differentiable SLAM architectures in a self-supervised manner to train end-to-end deep learning models in various LiDAR based applications. To the best of our knowledge there does not exist any work …
View article: Robust, High-Precision GNSS Carrier-Phase Positioning with Visual-Inertial Fusion
Robust, High-Precision GNSS Carrier-Phase Positioning with Visual-Inertial Fusion Open
Robust, high-precision global localization is fundamental to a wide range of outdoor robotics applications. Conventional fusion methods use low-accuracy pseudorange based GNSS measurements ($>>5m$ errors) and can only yield a coarse regist…
View article: SPENDER: A Platform for Secure and Privacy-Preserving Decentralized P2P E-Commerce
SPENDER: A Platform for Secure and Privacy-Preserving Decentralized P2P E-Commerce Open
The blockchain technology empowers secure, trustless, and privacy-preserving trading with cryptocurrencies. However, existing blockchain-based trading platforms only support trading cryptocurrencies with digital assets (e.g., NFTs). Althou…
View article: Generalized Data Weighting via Class-level Gradient Manipulation
Generalized Data Weighting via Class-level Gradient Manipulation Open
Label noise and class imbalance are two major issues coexisting in real-world datasets. To alleviate the two issues, state-of-the-art methods reweight each instance by leveraging a small amount of clean and unbiased data. Yet, these method…