Kodak
PulseAugur coverage of Kodak — every cluster mentioning Kodak across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New tool LIC-Audit tackles inconsistencies in image compression claims
A new paper introduces LIC-Audit, a tool designed to address inconsistencies in reported performance gains for learned image compression (LIC) methods. The research highlights that variations in reference software versi…
-
New FMT image compression format offers fixed-time, parallel GPU decoding
Researchers have introduced FMT (Fixed-step Multiscale Tree), a novel lossless image compression format designed for highly efficient and fixed-time decoding. Unlike existing learned codecs that can be slow, FMT utilize…
-
Study questions value of expensive image demosaicing methods
A new analysis explores the cost-effectiveness of different image demosaicing methods, which reconstruct full-color images from single-sensor data. Researchers found that the quality gain from expensive edge-aware metho…
-
New CP-GS framework optimizes 2D Gaussian image representation
Researchers have developed CP-GS, a novel framework for 2D Gaussian image representation that optimizes both capacity and precision under a shared rate constraint. This method dynamically reallocates Gaussian budgets to…
-
New PICA framework enhances image compression with adaptive multi-agent system
Researchers have developed PICA, a novel multi-agent framework designed to enhance image compression by adapting existing codecs to diverse scenarios and degraded inputs. This system utilizes four collaborative agents—P…
-
Printer ink costs more than vintage champagne per milliliter
Printer ink is surprisingly expensive, with some inkjet cartridges costing as much as $11.00 per milliliter. This high cost is driven by various manufacturers, including major players like HP Inc., Epson, and Canon.
-
New BLI framework advances progressive image compression
Researchers have developed a new framework called Bound-Conditioned Latent Inference (BLI) for progressive image compression. This method treats the decoding of trits not just as discrete symbols but as interval constra…
-
New GR-GIC method improves image compression quality and speed
Researchers have developed GR-GIC, a novel generative image compression method that balances high perceptual quality with fast inference speeds. The method introduces Guided Refinement (GR) to improve reconstruction at …
-
New method enhances slimmable image compression with channel-level masks
Researchers have developed a novel channel-level mask guidance method for slimmable image compression. This approach allows for non-contiguous channel selection, enabling narrow models to utilize the most informative ch…
-
PerQ reframes image compression with inverse generative modeling
Researchers have introduced PerQ, a novel approach to neural image compression that addresses the trade-off between pixel fidelity and perceptual quality. PerQ reframes perceptual reconstruction as inverse generative mo…
-
AFP-GIC advances controllable generative image compression with lower latency
Researchers have developed Adaptive Fused Prior Transfer for Controllable Generative Image Compression (AFP-GIC), a new framework for image compression that aims to improve reconstruction quality at very low bitrates. A…
-
CRM implementation success hinges on changing user habits, not just tech
Implementing new technology, such as a customer relationship management (CRM) system, is often technically straightforward, but the real challenge lies in changing user behavior and ingrained habits. Tal Frankfurt, foun…
-
New language model advances generative image compression
Researchers have developed FLM, a novel frequency-aware language model designed for generative image compression. This model transforms images into discrete sequences of DCT coefficients, which FLM then uses to autoregr…
-
CubicSplat: New Differentiable Vector Graphics Method Achieves Faster Training and Better Quality
Researchers have developed CubicSplat, a novel differentiable vector rasterizer that addresses the challenges of optimizing vector graphics by introducing uniform polyline surrogates. This method ensures bounded geometr…
-
New method improves visual token communication with counterfactual refinement
Researchers have developed a new method called Gated Counterfactual Refinement for Communication (GCR-C) to improve visual token communication. This technique aims to optimize the selection of discrete tokens sent for t…
-
New research advances learned image compression for human and machine perception · 3 sources tracked
Three new research papers explore advancements in learned image compression. The first paper introduces a hierarchical latent representation with multiple scales to improve entropy modeling and achieve a 17.9% BD-rate r…
-
Innovation blind spots: How past success hinders future growth
Past success can create an "innovation blind spot" for organizations, leading to complacency and legacy thinking that hinders future growth. Companies that consistently win do so by treating innovation as an ongoing ope…
-
New methods estimate image similarity from compression error
Researchers have developed new methods to estimate the Structural Similarity Index (SSIM) from Mean Square Error (MSE) for DCT-based compressed images. These approaches approximate local MSE by redistributing global MSE…
-
Kodak launches $35 beginner-friendly 35mm film camera
Kodak has launched the EC35, a new 35mm film camera designed for beginners and priced at $35. The camera features a simple point-and-shoot design with a 25mm lens, fixed f/10 aperture, and a 1/100 second shutter speed. …
-
AI 3D Generator Landscape Lacks Clear Leader; Kodak Launches New Camera
The article discusses the difficulty in recommending a top AI 3D generator due to a lack of comprehensive testing. It highlights the need for more comparative analysis of these tools. The piece also mentions a new, affo…