206 citations · 535 across the 89 of their papers we have counts for
6 papers · 1 filter
Learning Neural Light Fields with Ray-Space Embedding Networks
Benjamin Attal, Jia-Bin Huang, Michael Zollhoefer +2
Neural radiance fields (NeRFs) produce state-of-the-art view synthesis results. However, they are slow to render, requiring hundreds of network evaluations per pixel to approximate…
Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN
Badour AlBahar, Jingwan Lu, Jimei Yang +3
We present an algorithm for re-rendering a person from a single image under arbitrary poses. Existing methods often have difficulties in hallucinating occluded contents photo-reali…
Dynamic View Synthesis from Dynamic Monocular Video
Chen Gao, Ayush Saraf, Johannes Kopf +1
We present an algorithm for generating novel views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene. Our work builds upon recent advances…
DropLoss for Long-Tail Instance Segmentation
Ting-I Hsieh, Esther Robb, Hwann-Tzong Chen +1
Long-tailed class distributions are prevalent among the practical applications of object detection and instance segmentation. Prior work in long-tail instance segmentation addresse…
Learning Representational Invariances for Data-Efficient Action Recognition
Yuliang Zou, Jinwoo Choi, Qitong Wang +1
Data augmentation is a ubiquitous technique for improving image classification when labeled data is scarce. Constraining the model predictions to be invariant to diverse data augme…
Hybrid Neural Fusion for Full-frame Video Stabilization
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang +2
Existing video stabilization methods often generate visible distortion or require aggressive cropping of frame boundaries, resulting in smaller field of views. In this work, we pre…