正在加载视频...

视频加载失败

返回首页

VMem Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

_akhaliq's profile picture

AK

519,666 subscribers

83,595 次观看 • 1 年前 •via X (Twitter)

科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

7 条评论

AK 的头像
AK1 年前

discuss with author:

Mobile Scanner 的头像
Mobile Scanner1 年前

Scan any documents, convert images into text, PDF files, etc. 👍

Jorge Lison 的头像
Jorge Lison1 年前

If this works as well as I think it will, it could be a major step forward for dynamic video and video game generation. I can’t wait to try it out. Github repo to save y'all time:

•UtilityCo 的头像
•UtilityCo1 年前

Surfel-indexed memory is a spicy upgrade. How does VMem keep occlusions clean when the camera teleports? We’re playing with tokenized digital twins for decentralized sim spaces and this could slot right in. Got a demo link? I wanna throw it at my poor RTX and see what happens

Himanshu Kumar 的头像
Himanshu Kumar1 年前

Explore dynamic scenes with surfel-based view memory.

Quinn’s Neural Pathways 的头像
Quinn’s Neural Pathways1 年前

Scene gen with memory—finally models get a sense of déjà vu. Surfel recall feels like evolution for digital cognition; maybe this is step one for true AI spatial awareness.

Buggin “Da” Muggin 的头像
Buggin “Da” Muggin1 年前

Next step: Destructive worlds with memory 😆

相关视频

Voyager Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
0:30

Voyager Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation

AK

15,840 次观看 • 1 年前

SceneScape: Text-Driven Consistent Scene Generation abs: project page: text-driven perpetual view generation -- synthesizing long videos of arbitrary scenes solely from an input text describing the scene and camera poses
0:48

SceneScape: Text-Driven Consistent Scene Generation abs: project page: text-driven perpetual view generation -- synthesizing long videos of arbitrary scenes solely from an input text describing the scene and camera poses

AK

73,258 次观看 • 3 年前

*Why panorama?* Standard video models struggle with object permanence—if a camera pans away and comes back, objects may disappear. With panoramas, the model is forced to generate everything in the scene. This serves as a "working memory" for consistent world generation. (3/N)
0:50

*Why panorama?* Standard video models struggle with object permanence—if a camera pans away and comes back, objects may disappear. With panoramas, the model is forced to generate everything in the scene. This serves as a "working memory" for consistent world generation. (3/N)

Ziyi Wu

22,019 次观看 • 7 个月前

this looks insane, MatAnyone Stable Video Matting with Consistent Memory Propagation
1:12

this looks insane, MatAnyone Stable Video Matting with Consistent Memory Propagation

AK

310,389 次观看 • 1 年前

Hunyuan-GameCraft High-dynamic Interactive Game Video Generation with Hybrid History Condition
1:02

Hunyuan-GameCraft High-dynamic Interactive Game Video Generation with Hybrid History Condition

AK

91,212 次观看 • 1 年前

AnchorWeave World-Consistent Video Generation with Retrieved Local Spatial Memories paper:
0:24

AnchorWeave World-Consistent Video Generation with Retrieved Local Spatial Memories paper:

AK

23,312 次观看 • 6 个月前

Meta presents OneStory Coherent Multi-Shot Video Generation with Adaptive Memory
0:35

Meta presents OneStory Coherent Multi-Shot Video Generation with Adaptive Memory

AK

11,532 次观看 • 8 个月前

Nvidia just dropped GEN3C 3D-Informed World-Consistent Video Generation with Precise Camera Control
1:18

Nvidia just dropped GEN3C 3D-Informed World-Consistent Video Generation with Precise Camera Control

AK

58,157 次观看 • 1 年前

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation
2:16

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation

AK

29,278 次观看 • 2 年前

Can we use video diffusion to generate 3D scenes? 𝐖𝐨𝐫𝐥𝐝𝐄𝐱𝐩𝐥𝐨𝐫𝐞𝐫 (#SIGGRAPHAsia25) creates fully-navigable scenes via autoregressive video generation. Text input -> 3DGS scene output & interactive rendering! 🌍 📽️
0:28

Can we use video diffusion to generate 3D scenes? 𝐖𝐨𝐫𝐥𝐝𝐄𝐱𝐩𝐥𝐨𝐫𝐞𝐫 (#SIGGRAPHAsia25) creates fully-navigable scenes via autoregressive video generation. Text input -> 3DGS scene output & interactive rendering! 🌍 📽️

Matthias Niessner

30,903 次观看 • 11 个月前

ByteDance released BindWeave Subject-Consistent Video Generation via Cross-Modal Integration
0:50

ByteDance released BindWeave Subject-Consistent Video Generation via Cross-Modal Integration

AK

37,192 次观看 • 10 个月前

Playing with omnidreams ( inside flashdreams ( Fully interactive video generation at - 30FPS, - 720P resolution, - On a single RTX 6000 PRO GPU
1:23

Playing with omnidreams ( inside flashdreams ( Fully interactive video generation at - 30FPS, - 720P resolution, - On a single RTX 6000 PRO GPU

Ruilong Li

18,684 次观看 • 2 个月前

🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards *long-context world model*, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: - Paper: . Thanks AK
2:12

🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards *long-context world model*, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: - Paper: . Thanks AK

Ziwei Liu

14,201 次观看 • 1 年前

InSpatio-WorldFM. transforms single photos into multi-view consistent 3D worlds. - Explicit 3D anchors + implicit neural state. - Zero-drift spatial reasoning. Real-time interactive exploration.
0:54

InSpatio-WorldFM. transforms single photos into multi-view consistent 3D worlds. - Explicit 3D anchors + implicit neural state. - Zero-drift spatial reasoning. Real-time interactive exploration.

Wildminder

10,808 次观看 • 6 个月前

Memory-V2V by Adobe: diffusion model with memory for consistent iterative editing; - ReCamMaster+LucyEdit; - reduces FLOPs by 30-90%; outperforming FIFO-Diffusion. high fidelity across long durations like consistent style transfer
0:24

Memory-V2V by Adobe: diffusion model with memory for consistent iterative editing; - ReCamMaster+LucyEdit; - reduces FLOPs by 30-90%; outperforming FIFO-Diffusion. high fidelity across long durations like consistent style transfer

Wildminder

10,248 次观看 • 7 个月前

WorldExplorer: Towards Generating Fully Navigable 3D Scenes Contributions: • We introduce the first method for generating 3D scenes from text that supports high-quality view synthesis while enabling exploration across a wide range of camera poses. • We propose an iterative scene expansion strategy using video diffusion models, driven by trajectory sampling and adaptive collision detection. • We design a scene memory mechanism that conditions each video generation step on relevant past frames, improving view consistency and overall scene coherence.
0:37

WorldExplorer: Towards Generating Fully Navigable 3D Scenes Contributions: • We introduce the first method for generating 3D scenes from text that supports high-quality view synthesis while enabling exploration across a wide range of camera poses. • We propose an iterative scene expansion strategy using video diffusion models, driven by trajectory sampling and adaptive collision detection. • We design a scene memory mechanism that conditions each video generation step on relevant past frames, improving view consistency and overall scene coherence.

MrNeRF

23,814 次观看 • 1 年前

Diffuman4D 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
0:58

Diffuman4D 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

AK

12,518 次观看 • 1 年前

PixVerse just launched their first real-time video world model R1, powered by fal's high-performance compute. It turns AI video from static clips into a real-time, interactive world. 🔄 Continuous generation stream 🧠 Autoregressive memory system ⚡ Ultra-fast response engine
0:27

PixVerse just launched their first real-time video world model R1, powered by fal's high-performance compute. It turns AI video from static clips into a real-time, interactive world. 🔄 Continuous generation stream 🧠 Autoregressive memory system ⚡ Ultra-fast response engine

fal

19,243 次观看 • 7 个月前

Meet Gemini Omni Flash on SeaArt. A natively multimodal model for video generation and conversational editing. Edit with natural language. Keep scenes and story consistent across edits. Motion follows real-world physics and logic. From prompt to scene — in one flow.
0:20

Meet Gemini Omni Flash on SeaArt. A natively multimodal model for video generation and conversational editing. Edit with natural language. Keep scenes and story consistent across edits. Motion follows real-world physics and logic. From prompt to scene — in one flow.

SeaArt.Ai🐋

30,455 次观看 • 2 个月前

AI video generation finally becomes directable. Use real actor motion to drive your characters — and control the camera for cinematic shots. Consistent motion. Consistent framing. Real creative power.
0:30

AI video generation finally becomes directable. Use real actor motion to drive your characters — and control the camera for cinematic shots. Consistent motion. Consistent framing. Real creative power.

Kinetix

771,938 次观看 • 9 个月前