Oldies but goldies: R. Keys, Cubic convolution interpolation for... digital image processing, 1980. Introduces bicubic interpolation, the most frequently used image interpolation method.show more

😀 ToonCrafter: Generative Cartoon Interpolation 🔆 Can interpolate two... cartoon images by leveraging the pre-trained image-to-video diffusion priors. Model on 🤗👇show more

The Stable Video Diffusion model just dropped 🔥 The... new model supports: – Text-to-Video – Image-to-Video – 14 or 25 frames at 576 x 1024 – Multi-View Generation – Frame Interpolation – 3D Scene Understanding – Camera Control via LoRA Paper: Code: SVD model: SVD-XT model:show more

Oldies but goldies: Y Nesterov, A method for solving... a convex programming problem with convergence rate O(1/k^2). Improves the 1/k rate of vanilla gradient descent to 1/k^2.show more

3. Modify image Use this prompt to modify the... image you have chosen: "Modify image [1] with seed [1470033597]: add a parrot on her shoulder" Dall-E 3 identifies the image and makes the changes for you! Tips and tricks: - You can generate as many variations as you like. - It's also possible to remove an element from the image using the same method. - Sometimes the image isn't 100% identical, but still looks very similar.show more

🎥 Comparing AI video models: Image to video •... Gen-3 • Kling AI 1.5 • Hailuo MiniMax • Luma Dream Machine I used a Midjourney image in each model 4 times with no text prompt. This type of image is difficult for the AI to separate the subject in the front from the people behind her - they tend to move the group as if they are a single unit. But the results were interesting, as you can see! I chose my favorite results, below.show more

We recently discovered the ultimate workflow to restore old... footage to something close to digital high-quality footage. The method works better than we thought, and it utilizes OpenAI GPT-Image 2 + seedance2.0 2.0 + Topaz Labs Astra…. See the step-by-step workflow in 🧵 Shoutout to Adam Nieri from our team for the real footage + test!show more

🪽 Hermes just got more creative! —— Risomorphism-1911 —... production-grade ASCII rendering pipeline 🎨 Hermes-native ASCII art engine. 4 presets, --scale 1–16, video→animated eikon pipeline for your Herm TUI, quality-gated verdicts, pure-Python backend. Shipped, tested, gallery-stocked. Ready for operator deployment. 🧵 --- What it is Risomorphism-1911 is the ASCII rendering foundation for Hermes ops. Still images, video, animated eikons — all from a single deterministic pipeline. No external binaries. No guesswork. Quality enforced at every step. --- Capabilities - 4 presets: stroke-clarity (high-contrast poster), d30-dense (180-glyph block mode), braille-detail (4× effective resolution), eikon-motion (video pipeline) - Integer scaling: --scale N (1–16) on base 48×24 grid; intermediate grids adapt automatically - Quality gates: automatic verdict — high-contrast (production-safe), low-contrast-garble-risk (auto-reject), braille-dominant (resolution boost detected) - Video pipeline: frame extraction → motion-phase detection → optional motion-compensated interpolation (48 fps) → embedded HTML5 player (no HTTP/CORS) - Edge-aware processing: Laplacian-weighted downsampling + CLAHE preserves structural edges even at scale-16 densities - Pure-Python runtime: Pillow + NumPy only; ffmpeg optional for interpolation step --- CLI surface ascii-pipeline presets # list 4 presets ascii-pipeline diagnose file.txt # quality verdict ascii-pipeline render-preview image.jpg # quick PNG ascii-pipeline render-image \ --input image.jpg \ --preset d30-dense \ --scale 4 \ --out out.txt \ --preview-out out.png \ --diagnostics-out out.json ascii-pipeline build-eikon-from-video \ --video owl.mp4 \ --fps 48 \ --states 3 \ --id owl-smooth --- Scale strategy - Base: 48×24 (Herm avatar) - Scale 1–4: deployable, fast - Scale 8: showcase-ready - Scale 16: poster-sized, heavy, edge-aware mandatory All paths share the same preset pipeline; intermediate grids scale transparently. --- Tech stack - Python 3.11+, Pillow ≥10.0, NumPy ≥1.26 - Zero runtime binary deps - 11-test suite, 100% green - MIT license - Skill documented in SKILL.md with operator guidance --- Gallery (16 panels) - Cosmic pyramid stroke-clarity 192×96 — bold poster contrast - Cosmic pyramid D30 dense 192×96 — 180-glyph atmospheric - Owl animated eikon 48 fps — motion phases, smooth interpolation - Avatar fallback 48×24 — compact, deployable, legible All final-generation assets only. Clean tree: ~47 MB. No intermediates. --- This is the ASCII rendering baseline Hermes ops can rely on. Deterministic. Quality-gated. Production-ready.show more

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper... page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.show more

NeuRBF: A Neural Fields Representation with Adaptive Radial Basis... Functions paper page: present a novel type of neural fields that uses general radial bases for signal representation. State-of-the-art neural fields typically rely on grid-based representations for storing local neural features and N-dimensional linear kernels for interpolating features at continuous query points. The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals. Our method instead builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. To further improve the channel-wise capacity of radial basis functions, we propose to compose them with multi-frequency sinusoid functions. This technique extends a radial basis to multiple Fourier radial bases of different frequency bands without requiring extra parameters, facilitating the representation of details. Moreover, by marrying adaptive radial bases with grid-based ones, our hybrid combination inherits both adaptivity and interpolation smoothness. We carefully designed weighting schemes to let radial bases adapt to different types of signals effectively. Our experiments on 2D image and 3D signed distance field representation demonstrate the higher accuracy and compactness of our method than prior arts. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.show more

Even if you shut off white balance, most of... the pictures I see aren't selling how orange the sky is, because there's no frame of reference. Here's a 6500k display with an image we all recognize, for a more relative perspective. The color science isn't perfect, but close enough.show more

Q. you secretly save members meme 🐕 this is... my wallpaper 🌰 ohyul has the most photos. i used to have a lot of goofy shots 🐈‍⬛ it would be really fun if those photos could be made public 🌰 but he's been on top of managing his image so it’s less fun now 😭😭😭😭😭show more

Made with GPT Image 2 + Seedance 2.0 by... Yapper Prompt: Aurban city street, consistent young adult male same from reference Image (short dark hair, casual clothing), full-body framing, fixed side camera, slight gradual zoom-in, smooth interpolation, high character consistency Timeline Breakdown (15 seconds total) 0.0s – 1.5s | Scene 1 — Introduction young man standing still holding skateboard vertically at his side, relaxed posture, neutral expression, quiet city street background, no motion 1.5s – 3.0s | Scene 2 — Setup he lowers skateboard to ground and steps onto it, slight crouch, arms relaxed for balance, subtle anticipation 3.0s – 5.0s | Scene 3 — Rolling he rides forward smoothly, knees slightly bent, body leaning forward, light motion lines, slight background blur begins 5.0s – 6.5s | Scene 4 — Trick Preparation he crouches deeper, back foot pressing tail, front foot ready, arms widen, tension builds before jump 6.5s – 8.0s | Scene 5 — Ollie Jump he pops the board and jumps, skateboard rises with him, mid-air suspension, knees bent, strong motion lines 8.0s – 9.5s | Scene 6 — Landing he lands cleanly and continues riding, now wearing open casual jacket, expression more confident 9.5s – 11.5s | Scene 7 — Speed Increase he rides faster, leaning slightly, stronger motion blur, dynamic lines emphasize speed 11.5s – 13.5s | Scene 8 — Kickflip he performs kickflip, skateboard flips beneath him mid-air, controlled posture, high energy motion 13.5s – 15.0s | Scene 9 — Final Pose he lands and stabilizes, standing confidently on skateboard, now wearing full tracksuit jacket, relaxed stance, motion settles into still frame Motion & Style Controls motion strength: low (0–3s) medium (3–9s) high (9–13.5s) ease-out (final 1.5s) transitions: smooth interpolation between scenes camera: fixed side tracking + slight zoom-in across full 15s pacing: gradual acceleration then clean slowdownshow more

5-Axis CNC machining of turbocharger impellers sits in the... same league as aerospace manufacturing, precision engineering pushed to physical limits. These machines run with positional accuracy in the 1-5 micron range, spindle speeds of 20,000-40,000 RPM, and continuous 5-axis interpolation to carve complex blade geometry without collision, vibration, or thermal drift during cutting of nickel alloys and titanium. A production-grade 5-axis system for impellers typically costs $300,000 to $3 million+ The real constraint is not motion, but stability, suppressing chatter, tool deflection, and microscopic surface defects that would quietly destroy efficiency at 100,000+ RPM operating cycles. Without this class of machining, modern turbocharged engines, high-efficiency industrial compressors, and compact propulsion systems simply would not exist.show more

Is Google taking initial steps to enhance Street View?... For some reason, Street View seems stuck in technology that feels outdated. I wonder if we'll see such improvements on the product side. Also, note how much better it performs in all aspects compared to Zip-NeRF in their presented material. It offers more details and fewer artifacts. Great work! "LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering" Contributions: • We propose a novel LOD representation for 3DGS which, unlike previous methods [27, 28, 17], does not recompute the list of used Gaussians at each frame. This allows for acceleration and compaction, enabling the rendering of large-scale scenes even on mobile devices. • We design a strategy to automatically select optimal hyperparameters for splitting LODs, whereas most other methods require manual tuning of hyperparameters for each 3D scene. • To further accelerate rendering, we split the scene into chunks and pre-compute sets of active Gaussians per chunk. • Finally, we introduce a novel opacity interpolation scheme to produce visually pleasing rendering and eliminate artifacts when transitioning between chunks.show more

Playboi Carti ex girlfriend Gio went live to expose... him for being Gay😬 , says its not an image and be acts like that in real life but what hurt here the most was when she caught him in a room shirtless with 5 other guys 😬 “I had to let yall know” “Yall kept asking” “Gay”show more

A memory like this: I’ve been exploring Liquid Glass... for at least one year now, recreating many versions exactly nine all built with totally different techniques. I came to a realization. iOS 26, at least for me, missed part of the purpose. Liquid Glass is often used as decoration, while refraction could become the core of the user experience. Not an embellishment, but interaction itself. By turning a glass panel, refraction reveals something else: another app, another image, another portal. That’s when it clicked. You look through one image, turn slightly, and suddenly you’re somewhere else. Same moment, different feeling. I really hope Apple takes this approach to the next level. Vibecoded with WebGL.show more

Everyone's sleeping on image-to-3D AI models. They can make... your app look incredibly unique, with just a little effort. Here's how. This is my calorie tracker, built in a week with nothing but prompting. Just Claude Code + a couple APIs. The visuals are all AI-generated. I'll be sharing the full workflow + all the crazy technical stuff Claude and I did to make this work, so nobody has to struggle through it like me. Deep dive coming soon! Till then, this is the high-level idea: 1. Get a clean image of the food (or whatever your asset is) - In my app, the user describes foods via text, or attaches images (or both) - If text, an LLM extracts the food description and formats it into a specific prompt I tuned for this design, and we generate an image using Z-Image Turbo through fal - If image, we do the same thing but with FLUX.2 [dev] to edit the user image into our reference design - Originally, both used Google Nano Banana, but switching to open models cut costs and latency a ton 2. Gaussian splatting (2D image → 3D model) - I tried various 2D-to-3D options on fal and ended up with TripoSplat as my preferred balance of speed, cost, latency; this turns an image into a 3D model that looks super high quality (link below) - The app displays the 2D image while our backend generates the 3D splat - We "groom" the splat to reduce size and load time by culling low-opacity/scale points 3. Render efficiently on device Originally, it looked great but ran at 10 FPS. Getting to 120 FPS was a crazy journey. TL;DR: - SwiftUI had to go; it forced us to render each asset in independent MTKViews, which wasn't workable - Instead, we composite every dish into one full-bleed CAMetalLayer using MetalSplatter (link below) - We had to make some optimizations within MetalSplatter's code too, to reduce the overhead of sorting points per render Then I added some finishing touches like the subtle rotation and parallax as they move around. I think it turned out pretty cool :) Overall, this took some effort, but we still got it done in less than a day. Hopefully your agent can follow in the footsteps of mine and do it much faster. Keep an eye out for the bigger writeup, which'll give your agent everything it needs. If you have any questions, drop em below!show more

Must watch video!! 😉🙈 BBC Urdu is asking local... staff to declare Solangi's post about non payment of dues as fake news. While others did not agree till they are paid, one of the most decent local staff consented to do this for "image" of BBC and for the "credibility" of local staff / journos. But when Solangi demanded the proof, her tweet was deleted within 3 minutes. Poor Tarhub Asghar BBC News اردوshow more

AI videos are getting better but aren't quite perfect... yet - this one took loads of frames to produce! Anyway, enjoy this Rad Razor AI advert!💅 If you're keen, I'll break down my whole workflow, including how many frames it took and all the tools I used (had to combine 4 different AI video models and 3 image generators for this one) 🤫show more

🚀 The Segment Anything Model (SAM) has been upgraded... to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearchshow more