SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization
Multilayer-perceptrons (MLP) are known to struggle with learning functions of high-frequencies, and in particular cases with wide frequency bands. We present a spatially adaptive progressive encoding (SAPE) scheme for input signals of MLP networks, which enables them to better fit a wide range of frequencies without sacrificing training stability or requiring any domain specific preprocessing. SAPE gradually unmasks signal components with increasing frequencies as a function of time and space. The progressive exposure of frequencies is monitored by a feedback loop throughout the neural optimization process, allowing changes to propagate at different rates among local spatial portions of the signal space. We demonstrate the advantage of SAPE on a variety of domains and applications, including regression of low dimensional signals and images, representation learning of occupancy networks, and a geometric task of mesh transfer between 3D shapes.
Code (1)
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
A 2D Semantic-Aware Position Encoding for Vision Transformers
Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing positio…
PositionSemantic SimilaritySemantic Textual SimilarityTranslationOw\'oksape - An Online Language Learning Platform for Lakota
This paper presents Ow{\'o}ksape, an online language learning platform for the under-resourced language Lakota. The Lakota language (LakÈŸ{\'o}tiyapi) is a Siouan language native to the United States with fewer than 2000…
Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation
In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of…
Knowledge DistillationPose EstimationSpatially-Adaptive Hash Encodings For Neural Surface Reconstruction
Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction …
Surface ReconstructionRethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation
Autoregressive (AR) models, the theoretical performance benchmark for learned lossless image compression, are often dismissed as impractical due to prohibitive computational cost. This work re-thinks this paradigm, intro…
Image Compression