6 papers · 1 filter
PIXLRelight: Controllable Relighting via Intrinsic Conditioning
Miguel Farinha, Ronald Clark
We present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting control (e.g. through text or…
Reg4Pru: Regularisation Through Random Token Routing for Token Pruning
Julian Wyatt, Ronald Clark, Irina Voiculescu
Transformers are widely adopted in modern vision models due to their strong ability to scale with dataset size and generalisability. However, this comes with a major drawback: comp…
Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
Jacob Lin, Edward Gryspeerdt, Ronald Clark
There has been great progress in improving numerical weather prediction and climate models using machine learning. However, most global models act at a kilometer-scale, making it c…
Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image
Jerred Chen, Ronald Clark
In many robotics and VR/AR applications, fast camera motions lead to a high level of motion blur, causing existing camera pose estimation methods to fail. In this work, we propose…
Instant Uncertainty Calibration of NeRFs Using a Meta-Calibrator
Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi +1
Although Neural Radiance Fields (NeRFs) have markedly improved novel view synthesis, accurate uncertainty quantification in their image predictions remains an open problem. The pre…
Volumetric Cloud Field Reconstruction
Jacob Lin, Miguel Farinha, Edward Gryspeerdt +1
Volumetric phenomena, such as clouds and fog, present a significant challenge for 3D reconstruction systems due to their translucent nature and their complex interactions with ligh…