Pixel Compact
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
The best Qi2 batteries for iPhone and Pixel
Compact power banks have gotten a lot faster in the past year — and it’s not just their USB-C charging speeds that have received a boost. The newest Qi2.2-certified models can wirelessly charge an iPhone 16 or later at up to 25W. Combine that with their ability to magnetically snap on via MagSafe, and you’ve got yourself an essential add-on that’s easy to take on the go. Qi2 is a magnetic wireless charging standard that’s based on Apple’s MagSafe tech, so almost all modern iPhones support it.
Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
Announce Type: replace Abstract: Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried in hours of mostly redundant and irrelevant content. While agentic pipelines improve video reasoning capabilities, prevailing frameworks rely on a query-agnostic captioner to perceive video information, which wastes computation on irrelevant content and blurs fine-grained temporal and spatial information. Motivated by...
Near-UV Single-Pixel Imaging with All-Inorganic Lead-Free Perovskite
arXiv:2606.01731v1 Announce Type: new Abstract: Single-pixel imaging (SPI) is a powerful computational imaging technology that reconstructs spatial information from sequentially encoded optoelectrical signals without pixelated detector arrays. Solution-processible metal halide perovskites are promising photoactive candidates for SPI, but the toxicity of lead-based compositions remains a critical barrier to practical development. Here, we demonstrate one-step fabrication of low-dimensional,...
ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Deblurring
Electrical Engineering and Systems Science > Image and Video Processing [Submitted on 4 Jun 2026] Title:ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Deblurring View PDF HTML (experimental)Abstract:We introduce ErA (Error-Aware Deep Unrolling Network), an end-to-end frame work for single-image defocus deblurring.
Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detection
arXiv:2506.10601v2 Announce Type: replace Abstract: Given its ability to reduce annotation costs, weakly supervised learning based on single-point annotations has emerged as a research focus in oriented object detection. Compared with the classical teacher-student paradigm, the simple model paradigm (e.g., PointOBB-v2) can substantially further reduce resources required for training while ensuring strong performance.
InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space
Announce Type: new Abstract: Language-guided photo retouching aims to adjust color and tone while preserving geometry and texture. Recently, diffusion-based retouching shows a superior visual quality, but often struggles with both fidelity issues due to its generative nature and efficiency because of its iterative sampling process. In this work, we propose an efficient and fidelity-preserving retouching method using bilateral space manipulation, which is both compact and content-decoupled.
Neutrino Fingerprints: Image-Based Encodings of IceCube Events for CNN Direction Reconstruction
arXiv:2606.02788v1 Announce Type: cross Abstract: Reconstructing the direction of incoming neutrinos in the IceCube Neutrino Observatory is an important problem in astrophysics. The public IceCube--Neutrinos in Deep Ice Kaggle competition provided 140 million simulated events to benchmark reconstruction techniques.
Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation
arXiv:2606.01621v1 Announce Type: new Abstract: Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as low-level action prediction, an interface that is ambiguous, tied to short-horizon motion primitives, and inefficient due to repeated VLM querying. We propose Goal2Pixel, a pure pixel-based paradigm that reformulates VLN-CE as navigable pixel grounding.
Best Sleep Trackers of 2026: Oura, Whoop, and Eight Sleep
One of the most notable shifts in sleep technology is the transition from passive tracking to active guidance. Increasingly, consumer sleep trackers are offering AI-driven coaching and personalized recommendations that help users translate data into healthier habits. When thoughtfully implemented, this evolution has meaningful potential to improve outcomes.
VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
arXiv:2605.31466v1 Announce Type: new Abstract: Reconstructing the complete geometry of a scene from a single RGB image remains challenging - especially when inferring hidden structures where visual evidence is incomplete. We introduce VolFill, a generative framework that predicts the 3D structure of the complete scene rather than relying on traditional pixel-aligned regression. Our method utilizes a hybrid 3D VAE to compress sparse truncated unsigned distance function grids into a compact...