2D Neural Fields with Learned Discontinuities
Effective representation of 2D images is fundamental in digital image processing, where traditional methods like raster and vector graphics struggle with sharpness and textural complexity respectively. Current neural fields offer high-fidelity and resolution independence but require predefined meshes with known discontinuities, restricting their utility. We observe that by treating all mesh edges as potential discontinuities, we can represent the magnitude of discontinuities with continuous variables and optimize. Based on this observation, we introduce a novel discontinuous neural field model that jointly approximate the target image and recovers discontinuities. Through systematic evaluations, our neural field demonstrates superior performance in denoising and super-resolution tasks compared to InstantNGP, achieving improvements of over 5dB and 10dB, respectively. Our model also outperforms Mumford-Shah-based methods in accurately capturing discontinuities, with Chamfer distances 3.5x closer to the ground truth. Additionally, our approach shows remarkable capability in handling complex artistic drawings and natural images.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingSuper-ResolutionVector GraphicsSimilar Papers 제목 키워드 기반
MARF: The Medial Atom Ray Field Object Representation
We propose Medial Atom Ray Fields (MARFs), a novel neural object representation that enables accurate differentiable surface rendering with a single network evaluation per camera ray. Existing neural ray fields struggle …
ObjectRetrievalOperationalizing Quantized Disentanglement
Recent theoretical work established the unsupervised identifiability of quantized factors under any diffeomorphism. The theory assumes that quantization thresholds correspond to axis-aligned discontinuities in the probab…
Vision based Crop Row Navigation under Varying Field Conditions in Arable Fields
Accurate crop row detection is often challenged by the varying field conditions present in real-world arable fields. Traditional colour based segmentation is unable to cater for all such variations. The lack of comprehen…
NavigateNeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation
In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. Each representation is suited for different tasks thus making the transfo…
3D geometry3D Shape RepresentationAn InSAR Phase Unwrapping Framework for Large-scale and Complex Events
Phase unwrapping remains a critical and challenging problem in InSAR processing, particularly in scenarios involving complex deformation patterns. In earthquake-related deformation, shallow sources can generate surface-b…