pyramid
Learning Differential Pyramid Representation for Tone Mapping
Existing tone mapping methods operate on downsampled inputs and rely on handcrafted pyramids to recover high-frequency details. Existing tone mapping methods operate on downsampled inputs and rely on handcrafted pyramids to recover high-frequency details. These designs typically fail to preserve fine textures and structural fidelity in complex HDR scenes. Furthermore, most methods lack an effective mechanism to jointly model global tone consistency and local contrast enhancement, leading to globally flat or locally inconsistent outputs such as halo artifacts. We present the Differential Pyramid Representation Network (DPRNet), an end-to-end framework for high-fidelity tone mapping. At its core is a learnable differential pyramid that generalizes traditional Laplacian and Difference-of-Gaussian pyramids through content-aware differencing operations across scales. This allows DPRNet to adaptively capture high-frequency variations under diverse luminance and contrast conditions. To enforce perceptual consistency, DPRNet incorporates global tone perception and local tone tuning modules operating on downsampled inputs, enabling efficient yet expressive tone adaptation.
Parameter-Inverted Image Pyramid Networks
Image pyramids are commonly used in modern computer vision tasks to obtain multi-scale features for precise understanding of images. However, image pyramids process multiple resolutions of images using the same large-scale model, which requires significant computational cost. To overcome this issue, we propose a novel network architecture known as the Parameter-Inverted Image Pyramid Networks (PIIP). Our core idea is to use models with different parameter sizes to process different resolution levels of the image pyramid, thereby balancing computational efficiency and performance. Specifically, the input to PIIP is a set of multi-scale images, where higher resolution images are processed by smaller networks. We further propose a feature interaction mechanism to allow features of different resolutions to complement each other and effectively integrate information from different spatial scales. Extensive experiments demonstrate that the PIIP achieves superior performance in tasks such as object detection, segmentation, and image classification, compared to traditional image pyramid methods and single-branch networks, while reducing computational cost. Notably, when applying our method on a large-scale vision foundation model InternViT-6B, we improve its performance by 1\%-2\% on detection and segmentation with only 40\%-60\% of the original computation. These results validate the effectiveness of the PIIP approach and provide a new technical direction for future vision computing tasks.
Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis
Time series analysis finds wide applications in fields such as weather forecasting, anomaly detection, and behavior recognition. Previous methods attempted to model temporal variations directly using 1D time series. However, this has been quite challenging due to the discrete nature of data points in time series and the complexity of periodic variation. In terms of periodicity, taking weather and traffic data as an example, there are multi-periodic variations such as yearly, monthly, weekly, and daily, etc. In order to break through the limitations of the previous methods, we decouple the implied complex periodic variations into inclusion and overlap relationships among different level periodic components based on the observation of the multi-periodicity therein and its inclusion relationships. This explicitly represents the naturally occurring pyramid-like properties in time series, where the top level is the original time series and lower levels consist of periodic components with gradually shorter periods, which we call the periodic pyramid. To further extract complex temporal variations, we introduce self-attention mechanism into the periodic pyramid, capturing complex periodic relationships by computing attention between periodic components based on their inclusion, overlap, and adjacency relationships. Our proposed Peri-midFormer demonstrates outstanding performance in five mainstream time series analysis tasks, including short-and long-term forecasting, imputation, classification, and anomaly detection.
Father of alien archaeology says the pyramids were not built by human hands... and claims he has proof
Prince Harry and Meghan Markle's Sundance screening sparks online row: 'Sussex Squad' brand claims event failed to sell out as'lies' despite photos showing'rows of empty seats' Mick Jagger's family launch desperate hunt for missing relative: His granddaughter's partner vanishes in Cornwall after wandering streets Forensic video analysis of Alex Pretti's final 30 seconds exposes'John Wayne gun' question that can't be ignored Sinister truth about Celine Dion's song All By Myself: Singer's producer reveals bombshell secrets of her 26-year age gap marriage... that he swore not to tell until her husband René died The nastiest clique in Hollywood have had their dirty secret outed... there's no coming back from this: MAUREEN CALLAHAN Ariana Grande and Cynthia Erivo'creeped a lot of people out' says anonymous Oscar voter amid Wicked snubs John Fetterman's own WIFE turns on him over ICE as Senator comes under fire for his silence on shooting of Alex Pretti Lauren Sanchez turns heads in a red skirt suit as she holds hands with billionaire husband Jeff Bezos at Schiaparelli's Paris Haute Couture Fashion Week show Olivia Wilde blasts'inauthentic and unrealistic' sex in modern film and claims it has'been that way for a long time' - despite featuring racy scenes in Don't Worry Darling Sandra Bullock's Blind Side costar Quinton Aaron is'fighting for his life' in hospital after falling at home Seedy underbelly of America's exclusive golf clubs... as cart girls expose ultra-rich world of sex scandals and drunken debauchery Real estate mogul is sensationally found GUILTY of murdering football coach's son outside mall Kelly Clarkson on verge of QUITTING: Staff are all starting to say same thing backstage... as friends let slip the only way she could be convinced to stay Panicking realtors are drowning in unsold homes in America's'most extreme' market. They blame'the Joe Rogan effect' Father of alien archaeology says the pyramids were not built by human hands... and claims he has proof READ MORE: Egypt's Great Pyramid construction rewritten as new evidence exposes how it was actually built The belief that the pyramids were not built by human hands has fascinated conspiracy theorists for decades. No one promoted that idea more persistently than Swiss author Erich von Däniken, often described as the father of ancient alien archaeology. Von Däniken, who died this month aged 90, argued that extraterrestrial visitors played a direct role in helping ancient Egyptians construct monuments that would otherwise have been impossible. In his 1968 bestseller'Chariots of the Gods,' he claimed alien'astronauts' visited early civilizations, including the ancient Egyptians and Mayans, and shared advanced technology.