4 papers
Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses
Ruxiao Duan, Erin Hong, Dongxu Zhao +3
Feed-forward foundation models for multi-view 3-dimensional (3D) reconstruction have been trained on large-scale datasets of perspective images; when tested on wide field-of-view i…
Evidential Neural Radiance Fields
Ruxiao Duan, Alex Wong
Understanding sources of uncertainty is fundamental to trustworthy three-dimensional scene modeling. While recent advances in neural radiance fields (NeRFs) achieve impressive accu…
Tuning Out-of-Distribution (OOD) Detectors Without Given OOD Data
Sudeepta Mondal, Xinyi Mary Xie, Ruxiao Duan +2
Existing out-of-distribution (OOD) detectors are often tuned by a separate dataset deemed OOD with respect to the training distribution of a neural network (NN). OOD detectors proc…
Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning
Ruxiao Duan, Jieneng Chen, Adam Kortylewski +2
Replay-based methods in class-incremental learning (CIL) have attained remarkable success. Despite their effectiveness, the inherent memory restriction results in saving a limited…