Deep 3D World Models for Multi-Image Super-Resolution Beyond Optical Flow
This addresses a limitation in MISR for applications like aerial or multi-view imaging where camera positions vary widely, offering a more general solution than current burst photography settings.
The paper tackles the problem of multi-image super-resolution (MISR) under large geometric disparities between images, moving beyond optical flow-based methods. It introduces EpiMISR, which uses epipolar geometry and transformer-based radiance feature fields to achieve substantial improvements over state-of-the-art MISR methods in such challenging conditions.
Multi-image super-resolution (MISR) allows to increase the spatial resolution of a low-resolution (LR) acquisition by combining multiple images carrying complementary information in the form of sub-pixel offsets in the scene sampling, and can be significantly more effective than its single-image counterpart. Its main difficulty lies in accurately registering and fusing the multi-image information. Currently studied settings, such as burst photography, typically involve assumptions of small geometric disparity between the LR images and rely on optical flow for image registration. We study a MISR method that can increase the resolution of sets of images acquired with arbitrary, and potentially wildly different, camera positions and orientations, generalizing the currently studied MISR settings. Our proposed model, called EpiMISR, moves away from optical flow and explicitly uses the epipolar geometry of the acquisition process, together with transformer-based processing of radiance feature fields to substantially improve over state-of-the-art MISR methods in presence of large disparities in the LR images.