Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Nano is a depth-aware atmospheric haze plugin that uses ML depth estimation to add physically accurate fog and light scattering to your footage. Works *best* on log footage with visible light sources - it analyzes scene highlights then creates airlight (atmospheric scatter) and halation (light bloom) that responds to...

275,409 Aufrufe • vor 1 Jahr •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

MrNeRF

27,428 Aufrufe • vor 1 Jahr

THE DEPTH MAP TRICK THAT FIXED DANCE ACCURACY IN SEEDANCE 2.0 Feed the model a video of someone dancing and it tries to interpret everything- the person, the clothes, the lighting, the room, and somewhere in there, the movement. Feed it a depth map and there's nothing left to interpret but the motion. Most creators trying to transfer a dance to a character reference the source footage directly, then wonder why the choreography drifts. The problem isn't the model - it's that you handed it ten variables when you only wanted one. Here's the workflow 1. Lock the character reference in GPT Image 2 first -face, build, costume, so identity holds independently of whatever motion gets applied to it 2. Convert the source dance footage into a depth map instead of using the raw video -this strips out the original performer's appearance, clothing, and environment entirely 3. Feed the depth map as the motion reference and the character sheet as the identity reference- two separate inputs doing two separate jobs, not one input trying to do both 5. Let the depth map carry only spatial movement -the model receives body position and momentum with no competing information about who's moving or what they look like 6. Keep the character and motion inputs isolated throughout - the moment you mix appearance data into the motion reference, the model starts negotiating between two identities Why this works • Raw footage passes the model everything at once- performer, wardrobe, room, lighting -and the choreography competes with all of it for attention • A depth map is pure spatial information, so the only thing left to transfer is movement • Separating identity from motion means the character can stay locked while the dance stays accurate - normally you're trading one for the other • The accuracy gain isn't the model getting better, it's the model getting fewer decisions to make Use cases: ⁃ Dance and choreography transfer onto original characters ⁃ Motion capture-style workflows without motion capture ⁃ Any sequence where a specific movement needs to survive intact ⁃ Character showcase content built on existing performance footage The character sheet answers who's dancing. The depth map answers how - and keeping those two questions separate is the whole trick.

Nexlow

84,925 Aufrufe • vor 24 Tagen

🚨 SCIENTISTS JUST SHOWED THAT LIGHT CAN TWIST MATTER USING ITS MAGNETIC FIELD. For a long time, physicists assumed the magnetic component of light was far too weak to have any meaningful effect on matter compared to its electric field. New experiments are challenging that view. Researchers have demonstrated that intense, properly structured light can induce magnetization and even mechanical twisting in materials through its magnetic field alone. This is an extension of the inverse Faraday effect, but observed with greater strength and control than many expected. Why this matters: • It opens new ways to control magnetism and material properties using only light • Could lead to faster, more energy-efficient magnetic memory and spintronic devices • Offers a new tool for manipulating matter at the nanoscale without physical contact • Bridges optics and magnetism in ways that were previously difficult to achieve The deeper implication: Light is not just an information carrier under the right conditions, its magnetic field can directly reshape the magnetic and mechanical state of matter. This blurs the line between electromagnetic waves and material control. If these effects can be scaled and made practical, we may eventually use light itself as a precise tool to write magnetic information or mechanically actuate tiny structures, rather than relying solely on electric currents or physical forces. We’re discovering that light still has hidden capabilities we haven’t fully exploited. How do you think being able to control matter with light’s magnetic field could change technology in the next decade? Follow for more frontier optics, quantum materials, and light-matter physics.

TheNewPhysics

34,654 Aufrufe • vor 1 Monat