Related papers: Unit Region Encoding: A Unified and Compact Geomet…

Generalizable implicit neural representation (INR) enables a single continuous function, i.e., a coordinate-based neural network, to represent multiple data instances by modulating its weights or intermediate features using latent codes.…

In the field of seismic interpretation, univariate databased maps are commonly used by interpreters, especially for fault detection. In these maps, contrast between target regions and the background is one of the main factors that affect…

A rectangular floorplan is a partition of a rectangle into smaller rectangles such that no four rectangles meet at a single point. Rectangular floorplans arise naturally in a variety of applications, including VLSI design, architectural…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

The encoding of solutions in black-box optimization is a delicate, handcrafted balance between expressiveness and domain knowledge -- between exploring a wide variety of solutions, and ensuring that those solutions are useful. Our main…

We present a notion of geometry encoding suitable for machine learning-based numerical simulation. In particular, we delineate how this notion of encoding is different than other encoding algorithms commonly used in other disciplines such…

This paper introduces a novel unified representation of diffusion models for image generation and segmentation. Specifically, we use a colormap to represent entity-level masks, addressing the challenge of varying entity numbers while…

We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning. In those learning tasks, the raw image vectors may not provide enough representation for their intrinsic structures due to…

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…

Volume-based indoor scene reconstruction methods offer superior generalization capability and real-time deployment potential. However, existing methods rely on multi-view pixel back-projection ray intersections as weak geometric constraints…

In this paper, we present a GNN-based Line Segment Parser (GLSP), which uses a junction heatmap to predict line segments' endpoints, and graph neural networks to extract line segments and their categories. Different from previous floor plan…

We present a unified and compact scene representation for robotics, where each object in the scene is depicted by a latent code capturing geometry and appearance. This representation can be decoded for various tasks such as novel view…

We present a simple non-generative approach to deep representation learning that seeks equivariant deep embedding through simple objectives. In contrast to existing equivariant networks, our transformation coding approach does not constrain…

Conformal Autoencoders are a neural network architecture that imposes orthogonality conditions between the gradients of latent variables to obtain disentangled representations of data. In this work we show that orthogonality relations…

We present our approach to improve room classification task on floor plan maps of buildings by representing floor plans as undirected graphs and leveraging graph neural networks to predict the room categories. Rooms in the floor plans are…

The paper addresses the problem of energy compaction of dense 4D light fields by designing geometry-aware local graph-based transforms. Local graphs are constructed on super-rays that can be seen as a grouping of spatially and…

The task of room layout estimation is to locate the wall-floor, wall-ceiling, and wall-wall boundaries. Most recent methods solve this problem based on edge/keypoint detection or semantic segmentation. However, these approaches have shown…

Learning and recognition is a fundamental process performed in many robot operations such as mapping and localization. The majority of approaches share some common characteristics, such as attempting to extract salient features, landmarks…

An implementation-efficient finite alphabet decoder for polar codes relying on coarsely quantized messages and low-complexity operations is proposed. Typically, finite alphabet decoding performs concatenated compression operations on the…

Encoding and decoding models are widely used in systems, cognitive, and computational neuroscience to make sense of brain-activity data. However, the interpretation of their results requires care. Decoding models can help reveal whether…