Introducing MotionForesight: A very simple approach re-purposing video models... for forecasting future 3D scene flow given a short observed video context Trained with just 40k RGB human videos, it generalizes well to completely new home/office scenes! 1/nshow more

Checkout ObjectForesight! We tackle the problem of predicting future... 3D object trajectories given a past context, purely from human videos of everyday interactions! [1/n]show more

✨ Any static 3D assets ➡️ 4D dynamic worlds.... Introducing CHORD, a universal framework for generating scene-level 4D dynamic motion from any static 3D inputs. It generalizes surprisingly well across a wide range of objects 🤯 and can even be used to learn robotics manipulation policy 🤖! Project page: Dive deeper in a 🧵: 1/nshow more

The context size of video world models is only... a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3show more

Introducing “FlowCam: Training Generalizable 3D Radiance Fields w/o Camera... Poses via Pixel-Aligned Scene Flow”! We train a generalizable 3D scene representation self-supervised on datasets of raw videos, without any pre-computed camera poses or SFM! 1/nshow more

(1/n) 🚀 With FastVideo, you can now generate a... 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licensesshow more

📢📢📢 Check out XCube, a generative model for very-high... resolution 3D shapes and scenes! Project Page: Project Video: Props to Xuanchi Ren for leading this project!!!! [1/N]show more

Just observed that Gemini 3.7 Flash in Antigravity can... now analyze videos natively.. strange that it wasn't explicitly mentioned.. Anyways, a very great addition.. earlier the model had to use tools like ffmpeg or py scripts to extract frames and view individual images do build an context about the given video.. Now it's just so clean...show more

📢🚗✨ Excited to announce InfiniCube, our scalable generative model... for dynamic 3D driving scene generation with high fidelity and controllability! InfiniCube generates very large-scale (300m×400m ~ 100,000m^2), dynamic 3D driving scenes given HD maps, 3D bounding boxes, and text prompts as controls. Website: Props to Yifan Lu for leading this project!!!! [1/N]show more

DimensionX: Create Any 3D and 4D Scenes from a... Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.show more

Short video about the light falloff in this scene... i learned it from "Jose Vega" on youtube, It's a simple trick :D #b3d #environmentart #blender #3d #stylizedrendershow more

Wonderland: Navigating 3D Scenes from a Single Image Contributions:... • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.show more

MiniMax H3 is setting a new standard for AI... video editing. Ranked #1 in multiple video editing benchmarks, it can transform existing footage with just a reference video and a prompt. Change text, backgrounds, outfits or create a completely new visual direction, with incredible consistency.show more

I am blown away 🤯. Check this out! CameraCtrl... II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models TL;DR: "To enable broader exploration of dynamic scenes, our model can generate new video clips of the same scene based on previously generated content and user-provided camera trajectories. This approach maintains dynamic capabilities, accurate camera control, and scene consistency throughout the extended exploration." "Our model enables precise camera control across diverse scenarios while preserving dynamic scene elements, e.g." "Our method can generate videos with strong 3D consistency, which enables high-quality 3D reconstruction using the camera-controlled videos." Contributions: 1) A systematic data curation pipeline for constructing a dynamic video dataset with camera trajectory annotations; 2) A lightweight camera control injection module and corresponding training strategy that preserves dynamic video generation capabilities while adding camera control effect; 3) A clip-wise autoregressive generation recipe that enables extended range exploration of generated scenes.show more

We recently obtained the highest-resolution 3D images of the... human brain ever taken from outside the skull. This is the first look. Introducing Aleph, a research lab building brain interfaces for the telepathic future. (1/n)show more

FramePack: Generate Video Forever [NVIDIA ONLY] The creator of... ControlNet just dropped a new approach to generating videos in a PROGRESSIVE way--you can generate loooong videos with LOW VRAM (just 6GB) SUP3RMASS1VE wrote a 1-click launcher to run the Gradio app on your PC!show more

🚨 Seedance 2.5 just dropped, and AI video generation... has reached a new level. I tested it by creating a 3D Pixar-style short film 🤯 From one simple prompt, it generated impressive visuals, smooth motion, and a complete story flow. The best part? You can try Seedance 2.5 on Dola AI for free. No complicated setup. No technical workflow. Just describe your idea and start creating. #dola #ai #seedance2.5show more

We got a new custom LED screen table for... future convention setups… we knew just what video to test it with first 🤣show more

🔥🚨BREAKING: A petri dish filled with human brain cells... just learned to how to play DOOM Scientists at Cortical Labs have successfully trained a cluster of approximately 200,000 living human neurons, grown on a microelectrode array chip, to play the classic 3D video game DOOM.show more

NVIDIA just released a very impressive text-to-video paper. Video... Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:show more

Video diffusion models have strong implicit representations of 3D... shape, material, and lighting, but controlling them with language is cumbersome, and control is critical for artists and animators. GenLit connects these implicit representations with a continuous 5D control signal describing the direction and intensity of a point light source. This enables single-image near-field relighting of an image using a video diffusion model. We use a ControlNet-like approach and show that, with a small amount of synthetic data, GenLit generalizes to complex real-world images. Given a single image and the 5D lighting signal, GenLit creates a video of a moving light source that is inside the scene. It moves around and behind scene objects, producing effects such as shading, cast shadows, secularities, and interreflections with a realism that is hard to obtain with traditional inverse rendering methods. GenLit shows that it is possible to get continuous control over implicit physical processes within a video model. I think this is just the beginning and promises to make such models much more practical for creators. Shrisha Bharadwaj will present today at SIGGRAPH Asia Room: S423/S424, Level 4 @ 13:50 on 15 of Dec.show more