Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transforms images into latent representations, reduces computational demands compared to directly processing pixels and enhances the effectiveness and efficiency of the generation process. Prior methods, such as VQGAN, typically utilize 2D latent grids with fixed downsampling factors. However, these 2D tokenizations face challenges in managing the inherent redundancies present in images, where adjacent regions frequently display similarities. To overcome this issue, we introduce **T**ransformer-based 1-D**i**mensional **Tok**enizer (TiTok), an innovative approach that tokenizes images into 1D latent sequences. TiTok provides a more compact latent representation, yielding substantially more efficient and effective representations than conventional techniques. For example, a 256 × 256 × 3 image can be reduced to just **32** discrete tokens, a significant reduction from the 256 or 1024 tokens obtained by prior methods. Despite its compact nature, TiTok achieves competitive performance to state-of-the-art approaches. Specifically, using the same generator framework, TiTok attains **1.97** gFID, outperforming MaskGIT baseline significantly by 4.21 at ImageNet 256 × 256 benchmark. The advantages of TiTok become even more significant when it comes to higher resolution. At ImageNet 512 × 512 benchmark, TiTok not only outperforms state-of-the-art diffusion model DiT-XL/2 (gFID 2.74 vs. 3.04), but also reduces the image tokens by 64×, leading to **410× faster** generation process. Our best-performing variant can significantly surpasses DiT-XL/2 (gFID **2.13** vs. 3.04) while still generating high-quality samples **74× faster**. Codes and models are available at https://github.com/bytedance/1d-tokenizer

Earth observation is a fundamental tool for monitoring the evolution of land use in specific areas of interest. Observing and precisely defining change, in this context, requires both time-series data and pixel-wise segmentations. To that end, we propose the DynamicEarthNet dataset that consists of daily, multi-spectral satellite observations of 75 selected areas of interest distributed over the globe with imagery from Planet Labs. These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes. DynamicEarthNet is the first dataset that provides this unique combination of daily measurements and high-quality labels. In our experiments, we compare several established baselines that either utilize the daily observations as additional training data (semi-supervised learning) or multiple observations at once (spatio-temporal learning) as a point of reference for future research. Finally, we propose a new evaluation metric SCS that addresses the specific challenges associated with time-series semantic change segmentation. The data is available at: https://mediatum.ub.tum.de/1650201.

Temporal semantic scene understanding is critical for self-driving cars or robots operating in dynamic environments. In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points. To this end, we present an approach and a point-centric evaluation metric. Our approach determines a semantic class for every point while modeling object instances as probability distributions in the 4D spatio-temporal domain. We process multiple point clouds in parallel and resolve point-to-instance associations, effectively alleviating the need for explicit temporal data association. Inspired by recent advances in benchmarking of multi-object tracking, we propose to adopt a new evaluation metric that separates the semantic and point-to-instance association aspects of the task. With this work, we aim at paving the road for future developments of temporal LiDAR panoptic perception.

Many high-level video understanding methods require input in the form of object proposals. Currently, such proposals are predominantly generated with the help of neural networks that were trained for detecting and segmenting a set of known object classes, which limits their applicability to cases where all objects of interest are represented in the training set. We propose an approach that can reliably extract spatio-temporal object proposals for both known and unknown object categories from stereo video. Our 4D Generic Video Tubes (4D-GVT) method combines motion cues, stereo data, and data-driven object instance segmentation in a probabilistic framework to compute a compact set of video-object proposals that precisely localizes object candidates and their contours in 3D space and time.

We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate. Current state-of-the-art methods are far from reaching video frame rate and mostly rely on merging instance segmentation with semantic background segmentation, making them impractical to use in many applications such as robotics. Our approach relaxes this requirement by using an object detector but is still able to re-solve inter- and intra-class overlaps to achieve a non-overlapping segmentation. On top of a shared encoder-decoder backbone, we utilize multiple branches for semantic segmentation, object detection, and instance center prediction. Finally, our panoptic head combines all outputs into a panoptic segmentation and can even handle conflicting predictions between branches as well as certain false predictions. Our network achieves 32.6% PQ on MS-COCO at 23.5 FPS, opening up panoptic segmentation to a broader field of applications.

The objective of this paper is to compare the accuracy in location estimation which can be achieved in an indoor-scenario for WLAN and UMTS using RF-Fingerprinting with various metrics and distance norms. The measurements were done in a 20 m × 15 m office environment, using 4 3G Small Cells (Home NodeB) and 4 WLAN-APs. To create the radio map, fingerprints were taken within a grid of one meter. For location estimation a deterministic approach using Euclidean Distance norm with a WKNN algorithm was used based on RSS and AP-visibility as metrics. As a probabilistic approach a histogram comparison method has been applied using Kullback-Leibler-Divergence as a distance norm. It can be shown, that the accuracy in Indoor-RFFingerprinting with UMTS is comparable to the accuracy, which can be achieved in a similar WLAN-Testbed. Signal visibility is an alternative metric to RSS for interference limited systems, such as UMTS. As a conclusion UMTS Small Cells are an interesting alternative to WLAN for indoor RF-Fingerprinting, especially because the same hardware can be used for traffic and for localization purposes, since the pilot is not subjected to adaptive frequency hopping or power control, as it is the case in most WLAN installations for interference reduction.

Radiating cables (LCXs) are well established for indoor coverage and are applied for surveillance sensors. An answer to the upcoming need of low-cost indoor positioning was given by the WIPoS approach. This indoor navigation system is using radiating cables with RF fingerprinting based on power level evaluation. State-of-the-art LCXs are mainly designed for broadband indoor coverage. But different cable properties are required for indoor navigation purposes. In this paper the research results of LCX-types designed for indoor positioning are presented and discussed. Existing standard LCX-types are compared with specially designed periodic and non-periodic structures. The WIPoS research project aims at improving the indoor positioning resolution while maintaining the coverage properties.

This paper investigates the influence of horizontally inhomogeneous clouds on the accuracy of total ozone column retrievals from space. The focus here is on retrievals based on backscattered ultraviolet light measurements in Huggins bands in the range of 315-340 nm. It is found that simplifying the description of cloud properties in the ozone-retrieval algorithm studied can produce errors of up to 6%, depending on the error in the assumed cloud parameters. Yet another finding is the fact that independent pixel approximation suffices for ozone-retrieval algorithms. This was found using three-dimensional Monte Carlo radiative transfer calculations in the Huggins bands