Regularizing sparse-input radiance fields with visibility priors, simpler-solution depth supervision, and sparse flow priors improves novel view synthesis and depth estimation on multiple benchmarks.
PreCNet: Next-Frame Video Prediction Based on Predictive Coding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Predictive coding, currently a highly influential theory in neuroscience, has not been widely adopted in machine learning yet. In this work, we transform the seminal model of Rao and Ballard (1999) into a modern deep learning framework while remaining maximally faithful to the original schema. The resulting network we propose (PreCNet) is tested on a widely used next frame video prediction benchmark, which consists of images from an urban environment recorded from a car-mounted camera, and achieves state-of-the-art performance. Performance on all measures (MSE, PSNR, SSIM) was further improved when a larger training set (2M images from BDD100k), pointing to the limitations of the KITTI training set. This work demonstrates that an architecture carefully based in a neuroscience model, without being explicitly tailored to the task at hand, can exhibit exceptional performance.
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sparse Input View Synthesis: 3D Representations and Reliable Priors
Regularizing sparse-input radiance fields with visibility priors, simpler-solution depth supervision, and sparse flow priors improves novel view synthesis and depth estimation on multiple benchmarks.