10 papers
αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
Xiang Zhang, Yang Zhang, Lukas Mehl +3
Accurately modeling soft boundaries, e.g., hair and defocus blur, is a fundamental challenge in stereo conversion due to the ambiguous blending of foreground and background. Existi…
Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation
Karlis Martins Briedis, Markus Gross, Christopher Schroers
Recent optical flow estimation methods often employ local cost sampling from a dense all-pairs correlation volume. This results in quadratic computational and memory complexity in…
ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
Rui Song, Tianhui Cai, Markus Gross +5
Feedforward 3D Gaussian Splatting (3DGS) often struggles in trajectory-based sparse-view driving scenes. Existing Gaussian repair methods mainly target optimization-based 3DGS, whi…
DiV-INR: Extreme Low-Bitrate Diffusion Video Compression with INR Conditioning
Eren Ãetin, Lucas Relic, Yuanyi Xue +3
We present a perceptually-driven video compression framework integrating implicit neural representations (INRs) and pre-trained video diffusion models to address the extremely low…
Region-Adaptive Generative Compression with Spatially Varying Diffusion Models
Lucas Relic, Roberto Azevedo, Yang Zhang +3
Generative image codecs aim to optimize perceptual quality, producing realistic and detailed reconstructions. However, they often overlook a key property of human vision: our tende…
Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views
Xiang Zhang, Yang Zhang, Lukas Mehl +2
Soft boundaries, like thin hairs, are commonly observed in natural and computer-generated imagery, but they remain challenging for 3D vision due to the ambiguous mixing of foregrou…