7 papers
Refracting Reality: Generating Images with Realistic Transparent Objects
Yue Yin, Enze Tao, Dylan Campbell
Generative image models can produce convincingly real images, with plausible shapes, textures, layouts and lighting. However, one domain in which they perform notably poorly is in…
Room Envelopes: A Synthetic Dataset for Indoor Layout Reconstruction from Images
Sam Bahrami, Dylan Campbell
Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing al…
Towards Scalable Backpropagation-Free Gradient Estimation
Daniel Wang, Evan Markou, Dylan Campbell
While backpropagation--reverse-mode automatic differentiation--has been extraordinarily successful in deep learning, it requires two passes (forward and backward) through the neura…
Gaussian Alignment for Relative Camera Pose Estimation via Single-View Reconstruction
Yumin Li, Dylan Campbell
Estimating metric relative camera pose from a pair of images is of great importance for 3D reconstruction and localisation. However, conventional two-view pose estimation methods a…
ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimation
Mo Zhou, Jianwei Wang, Xuanmeng Zhang +5
This paper studies optical flow estimation, a critical task in motion analysis with applications in autonomous navigation, action recognition, and film production. Traditional opti…
PlückeRF: A Line-based 3D Representation for Few-view Reconstruction
Sam Bahrami, Dylan Campbell
Feed-forward 3D reconstruction methods aim to predict the 3D structure of a scene directly from input images, providing a faster alternative to per-scene optimization approaches. S…