Genre
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
OpenSTL provides a modular and extensible framework implementing various state-of-the-art methods. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow, and weather forecasting.
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning Qi Wang 1, 2 Junming Y ang 3 Y unbo Wang
Training offline RL models using visual inputs poses two significant challenges, i.e.,
Iterative Reachability Estimation for Safe Reinforcement Learning
We theoretically establish that our algorithms almost surely converge to locally optimal policies of our safe optimization framework.
SfPUEL: Shape from Polarization under Unknown Environment Light
DeepSfP (4), which is even comparable with the multiview SfP method P ANDORA (15). In addition, metallic and dielectric surfaces exhibit different polarization BRDFs under the same illumination, which causes AoLP maps to vary on different materials, further compounding the normal estimation problem.
ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling
From left to right: a) renderings, b) input images, c) normals.
