FlashVSR is a streaming, one-step diffusion-based video super-resolution framework with block-sparse attention and a Tiny Conditional Decoder. It reaches ~17 FPS at 768×1408 on a single A100 GPU. A Locality-Constrained Attention design further improves generalization and perceptual quality on ultra-high-resolution videos.
Stable Video Infinity (SVI) is able to generate ANY-length videos with high temporal consistency, plausible scene transitions, and controllable streaming storylines in ANY domains.
OpenSVI: Everything is open-sourced: training & evaluation scripts, datasets, and more.
Infinite Length: No inherent limit on video duration; generate arbitrarily long stories (see the 10‑minute “Tom and Jerry” demo).
Versatile: Supports diverse in-the-wild generation tasks: multi-scene short films, single‑scene animations, skeleton-/audio-conditioned generation, cartoons, and more.
Efficient: Only LoRA adapters are tuned, requiring very little training data: anyone can make their own SVI easily.
VISTA is a modular, configurable framework for optimizing text-to-video generation. Given a user video prompt P, it produces an optimized video V* and its refined prompt P* through two phases: (i) Initialization and (ii) Self-Improvement, inspired by the human video optimization process via prompting. During (i), the prompt is parsed and planned into variants to generate candidate videos (Step 1), after which the best video-prompt pair is selected (Step 2). In (ii), the system generates multi-dimensional, multi-agent critiques (Step 3), refines the prompt (Step 4), produces new videos, and reselects the champion pair (Step 2). This phase continues until a stopping criterion is met or the maximum number of iterations is reached.
We introduce a principle, Oz, for displaying color imagery: directly controlling the human eye’s photoreceptor activity via cell-by-cell light delivery. Theoretically, novel colors are possible through bypassing the constraints set by the cone spectral sensitivities and activating M cone cells exclusively. In practice, we confirm a partial expansion of colorspace toward that theoretical ideal. Attempting to activate M cones exclusively is shown to elicit a color beyond the natural human gamut, formally measured with color matching by human subjects. They describe the color as blue-green of unprecedented saturation. Further experiments show that subjects perceive Oz colors in image and video form. The prototype targets laser microdoses to thousands of spectrally classified cones under fixational eye motion. These results are proof-of-principle for programmable control over individual photoreceptors at population scale.
SeC (Segment Concept) is a breakthrough in video object segmentation that shifts from simple feature matching to high-level conceptual understanding. Unlike SAM 2.1 which relies primarily on visual similarity, SeC uses a Large Vision-Language Model (LVLM) to understand what an object is conceptually, enabling robust tracking through:
Semantic Understanding: Recognizes objects by concept, not just appearance
Scene Complexity Adaptation: Automatically balances semantic reasoning vs feature matching
Superior Robustness: Handles occlusions, appearance changes, and complex scenes better than SAM 2.1
SOTA Performance: +11.8 points over SAM 2.1 on SeCVOS benchmark
How SeC Works
Visual Grounding: You provide initial prompts (points/bbox/mask) on one frame
Concept Extraction: SeC’s LVLM analyzes the object to build a semantic understanding
Smart Tracking: Dynamically uses both semantic reasoning and visual features
Keyframe Bank: Maintains diverse views of the object for robust concept understanding
The result? SeC tracks objects more reliably through challenging scenarios like rapid appearance changes, occlusions, and complex multi-object scenes.
An incredible story. Vivian Maier was a nanny who lived in Chicago for most of her life and passed away in 2009 at the age of 83. Little more is known about her, except that she was an avid street photographer. Her work was discovered at an auction in 2007, more than 100,000 negatives and undeveloped rolls of film, sold by a storage facility who were cleaning out her locker for delinquent rent.
Shutter is the device that controls the amount of light through a lens. Basically in general it controls the amount of time a film is exposed. Shutter speed is how long this device is open for, which also defines motion blur… the longer it stays open the blurrier the image captured. The number refers to the amount of light actually allowed through.
As a reference, shooting at 24fps, at 180 shutter angle or 1/48th of shutter speed (0.0208 exposure time) will produce motion blur which is similar to what we perceive at naked eye
Talked of as in (shutter) angles, for historical reasons, as the original exposure mechanism was controlled through a pie shaped mirror in front of the lens.
A shutter of 180 degrees is blocking/allowing light for half circle. (half blocked, half open). 270 degrees is one quarter pie shaped, which would allow for a higher exposure time (3 quarter pie open, vs one quarter closed) 90 degrees is three quarter pie shaped, which would allow for a lower exposure (one quarter open, three quarters closed)
