正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Traditional SLAM: capture lidar, capture camera, fuse in post, correct drift, build map This is a Rev8 OS1 Max running SLAM down Union Street in San Francisco. The colorized point cloud is generated from a single sensor in a single pass, with color and depth captured in the same... show more

Ouster

8,342 subscribers

29,707 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

10.4 million points per second, 256 channels, color captured with depth in the same photon event Here is a Rev8 OS1 Max walkthrough of the Cathedral of Seville, taken in a single pass.

10.4 million points per second, 256 channels, color captured with depth in the same photon event Here is a Rev8 OS1 Max walkthrough of the Cathedral of Seville, taken in a single pass.

Ouster

13,913 次观看 • 24 天前

With Rev8, color is perceived in the right place, at the right distance, at the right moment. Ouster L4 silicon captures color and depth in the same photon event, with Fujifilm color science embedded directly on the chip. This is a Rev8 OS1 Max driving the Embarcadero in San Francisco. Every traffic signal, brake light, and bike lane resolved in 48-bit native color, perfectly aligned with depth at the silicon level.

With Rev8, color is perceived in the right place, at the right distance, at the right moment. Ouster L4 silicon captures color and depth in the same photon event, with Fujifilm color science embedded directly on the chip. This is a Rev8 OS1 Max driving the Embarcadero in San Francisco. Every traffic signal, brake light, and bike lane resolved in 48-bit native color, perfectly aligned with depth at the silicon level.

Ouster

29,617 次观看 • 3 个月前

This was captured without a camera. Every point carries its true 3D position and 48-bit native color, fused in the same photon event. Here is a palm-lined drive down Beverly Drive in Los Angeles, the trees, the road, and the light all captured with Rev8 lidar alone, accurate from 1 lux to 2 million lux.

This was captured without a camera. Every point carries its true 3D position and 48-bit native color, fused in the same photon event. Here is a palm-lined drive down Beverly Drive in Los Angeles, the trees, the road, and the light all captured with Rev8 lidar alone, accurate from 1 lux to 2 million lux.

Ouster

11,240 次观看 • 1 个月前

The team at NVIDIA AI Developer really nailed it with ViPE!! This SLAM system generated pose, depth, point clouds, etc, in a few seconds! Now to get the output to work with GEN3C... If you are interested in running this yourself, it took about 5 minutes to get up and running from scratch.

The team at NVIDIA AI Developer really nailed it with ViPE!! This SLAM system generated pose, depth, point clouds, etc, in a few seconds! Now to get the output to work with GEN3C... If you are interested in running this yourself, it took about 5 minutes to get up and running from scratch.

Jonathan Stephens

34,947 次观看 • 1 年前

LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM LEGO-SLAM running at 15 FPS on a ScanNet scene with language-based loop closing for drift correction. LEGO-SLAM is a 3DGS-based SLAM framework that supports open-vocabulary semantic querying and rendering. It tracks via G-ICP and efficiently builds a map by embedding Gaussians with scene-adaptive 16D language features. Map management is achieved through Language Pruning and Language-Based Loop Detection. The generated map enables open-vocabulary 3D Object Localization.

LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM LEGO-SLAM running at 15 FPS on a ScanNet scene with language-based loop closing for drift correction. LEGO-SLAM is a 3DGS-based SLAM framework that supports open-vocabulary semantic querying and rendering. It tracks via G-ICP and efficiently builds a map by embedding Gaussians with scene-adaptive 16D language features. Map management is achieved through Language Pruning and Language-Based Loop Detection. The generated map enables open-vocabulary 3D Object Localization.

Ryohei Sasaki@engineer

15,060 次观看 • 5 个月前

Second career grand slam for Jhonny Level is a moonshot! 🌕 The SFGiants' No. 4 prospect is slashing .444/.490/.889 for the Single-A San Jose Giants, leading the circuit in OPS (1.379):

Second career grand slam for Jhonny Level is a moonshot! 🌕 The SFGiants' No. 4 prospect is slashing .444/.490/.889 for the Single-A San Jose Giants, leading the circuit in OPS (1.379):

MLB Pipeline

67,551 次观看 • 4 个月前

Build Showcase is a series where we look at builds from the community. This Titan was put together by DeadRabbit and uses the latest in slam technology to warp around the map, blow up screens and chunk Pinnacle Bosses in seconds.

Build Showcase is a series where we look at builds from the community. This Titan was put together by DeadRabbit and uses the latest in slam technology to warp around the map, blow up screens and chunk Pinnacle Bosses in seconds.

Path of Exile

119,633 次观看 • 1 年前

Blackmagic Design just made a huge announcement at NAB 2025 — revealing their full immersive video workflow from camera to Apple Vision Pro. In this video, we walk through the Blackmagic URSA Cine Immersive pipeline, from capture in Blackmagic RAW, through DaVinci Resolve, all the way to native immersive playback on Apple Vision Pro using MV-HEVC metadata. We also sat down with Blackmagic Design to discuss the latest URSA Cine Immersive firmware and UIs update, immersive color grading workflows, and a powerful REST API that allows remote camera control — perfect for broadcast and remote Immersive 180 capture environments. Captured live at NAB 2025, this is the first in-depth look at how Blackmagic is setting a new standard for immersive filmmaking, delivering true 8K-per-eye playback with zero baked-in rendering and no double-pass quality loss. Comment “URSA Cine” for the full 30-minute in-depth video. #ursacineimmersive #applevisionpro #visionpro

Blackmagic Design just made a huge announcement at NAB 2025 — revealing their full immersive video workflow from camera to Apple Vision Pro. In this video, we walk through the Blackmagic URSA Cine Immersive pipeline, from capture in Blackmagic RAW, through DaVinci Resolve, all the way to native immersive playback on Apple Vision Pro using MV-HEVC metadata. We also sat down with Blackmagic Design to discuss the latest URSA Cine Immersive firmware and UIs update, immersive color grading workflows, and a powerful REST API that allows remote camera control — perfect for broadcast and remote Immersive 180 capture environments. Captured live at NAB 2025, this is the first in-depth look at how Blackmagic is setting a new standard for immersive filmmaking, delivering true 8K-per-eye playback with zero baked-in rendering and no double-pass quality loss. Comment “URSA Cine” for the full 30-minute in-depth video. #ursacineimmersive #applevisionpro #visionpro

Hugh Hou

13,935 次观看 • 1 年前

Made this video (🎶) with a Midjourney v6 image! Started by upscaling/refining with Magnific.ai, pulled a Marigold Depth Map from that in ComfyUI, then used as a displacement map in Blender where I animated this camera pass with some relighting and narrow depth of field.🧵1/12

Made this video (🎶) with a Midjourney v6 image! Started by upscaling/refining with Magnific.ai, pulled a Marigold Depth Map from that in ComfyUI, then used as a displacement map in Blender where I animated this camera pass with some relighting and narrow depth of field.🧵1/12

CoffeeVectors

135,713 次观看 • 2 年前

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 次观看 • 4 个月前

Motion capture is about to get easy. This is captured with a single iPhone using Move One, our new mobile app that uses AI to extract motion data from video. No suits or markers required. We are in invite only beta right now, waitlist link in the comments📱

Motion capture is about to get easy. This is captured with a single iPhone using Move One, our new mobile app that uses AI to extract motion data from video. No suits or markers required. We are in invite only beta right now, waitlist link in the comments📱

Move AI

200,998 次观看 • 3 年前

Photon Matrix is a portable laser mosquito defence system from Photon Matrix Lab, a startup in Changzhou, China. A lidar sweeps a fan-shaped plane, spots mosquito-sized targets by the change in distance, and a laser fires along the same optical path to disable the wings. The company claims up to 30 mosquitoes a second within a six-metre radius. #PhotonMatrix #LaserMosquitoKiller #Lidar

Photon Matrix is a portable laser mosquito defence system from Photon Matrix Lab, a startup in Changzhou, China. A lidar sweeps a fan-shaped plane, spots mosquito-sized targets by the change in distance, and a laser fires along the same optical path to disable the wings. The company claims up to 30 mosquitoes a second within a six-metre radius. #PhotonMatrix #LaserMosquitoKiller #Lidar

Interesting Engineering

17,637 次观看 • 25 天前

This is what it was like to drive on the Embarcadero Freeway in 1985. There was also a little variety in the billboards. Today, every single billboard in San Francisco exists to force AI down our throats.

This is what it was like to drive on the Embarcadero Freeway in 1985. There was also a little variety in the billboards. Today, every single billboard in San Francisco exists to force AI down our throats.

RetroBayArea

78,800 次观看 • 6 个月前

This is all on a single block in DC: -5 Below is shutting down due to theft -Target banned unaccompanied teens -CVS has no more items on the shelves -A street vendor selling the same items missing from CVS in front of CVS

This is all on a single block in DC: -5 Below is shutting down due to theft -Target banned unaccompanied teens -CVS has no more items on the shelves -A street vendor selling the same items missing from CVS in front of CVS

End Wokeness

652,450 次观看 • 2 年前

Full article capture to Notion on iPhone! This is a super early look at Flylighter on iOS. My team got this initial test build of the app up and running in a single month. Absolutely incredible. Next steps: ✅ Speed upgrades ✅ More capture modes - text highlights, voice recordings ✅ Capture history (so you can send a highlight to a previously captured page) Soon, you’ll have a full set of tools for capturing any idea or resource you find to Notion, instantly. Less friction = more action 💪

Full article capture to Notion on iPhone! This is a super early look at Flylighter on iOS. My team got this initial test build of the app up and running in a single month. Absolutely incredible. Next steps: ✅ Speed upgrades ✅ More capture modes - text highlights, voice recordings ✅ Capture history (so you can send a highlight to a previously captured page) Soon, you’ll have a full set of tools for capturing any idea or resource you find to Notion, instantly. Less friction = more action 💪

Thomas Frank

20,760 次观看 • 2 年前

This is Nvidia’s end to end autonomous vehicle model running in a Mercedes car going point to point through San Francisco with no interventions, one shot

This is Nvidia’s end to end autonomous vehicle model running in a Mercedes car going point to point through San Francisco with no interventions, one shot

Max Weinbach

204,505 次观看 • 8 个月前

Let me share a long-awaited behind-the-scenes video of how Simulon works. It all starts with setting up a scene. You set the location, lighting conditions and capture the light map with a few turns. After that, you can capture the environment mesh using the Lidar scanner. That's the moment the fun begins. You can bring in your #3D models with animations and capture a video of up to 50" using the #AR preview on screen. After that is done, you send the footage to the cloud and in a couple of minutes you get back an incredible #CGI shot. And this is just the beginning. Follow Gabriele Romagnoli to see how Simulon integrates with #Blender and in a full #VFX workflow. A special thanks to Divesh Naidoo for sharing early access and for building something 🤯

Let me share a long-awaited behind-the-scenes video of how Simulon works. It all starts with setting up a scene. You set the location, lighting conditions and capture the light map with a few turns. After that, you can capture the environment mesh using the Lidar scanner. That's the moment the fun begins. You can bring in your #3D models with animations and capture a video of up to 50" using the #AR preview on screen. After that is done, you send the footage to the cloud and in a couple of minutes you get back an incredible #CGI shot. And this is just the beginning. Follow Gabriele Romagnoli to see how Simulon integrates with #Blender and in a full #VFX workflow. A special thanks to Divesh Naidoo for sharing early access and for building something 🤯

Gabriele Romagnoli

142,698 次观看 • 2 年前

Seedance 2.5 is insane for marketing and UGC. I've already spent close to $6000 in generations and here's what I noticed: - Realism is on another level This entire vlog is generated. Freckles, flyaway hair, wind gusts, even the exposure shifts of a real phone camera. Nothing in this frame reads as AI. - Pay close attention to the video at 0:14 She flips the camera to show the valley and pans back to herself mid-sentence. Camera movement, lighting, and action like this all in a single pass were never possible before. - Voices finally sound human She talks to camera for the full 30 seconds. No robotic AI delivery, she breathes, pauses, and hits emotion like a real creator. - Up to 30 seconds in a single pass One take from start to finish. Characters don't drift and blocking works better than any other model. - Up to 50 inputs in one generation Feed your product, your creator, and your style references into a single run. UGC marketing will never be the same. Seedance 2.5 coming soon to Higgsfield.

Seedance 2.5 is insane for marketing and UGC. I've already spent close to $6000 in generations and here's what I noticed: - Realism is on another level This entire vlog is generated. Freckles, flyaway hair, wind gusts, even the exposure shifts of a real phone camera. Nothing in this frame reads as AI. - Pay close attention to the video at 0:14 She flips the camera to show the valley and pans back to herself mid-sentence. Camera movement, lighting, and action like this all in a single pass were never possible before. - Voices finally sound human She talks to camera for the full 30 seconds. No robotic AI delivery, she breathes, pauses, and hits emotion like a real creator. - Up to 30 seconds in a single pass One take from start to finish. Characters don't drift and blocking works better than any other model. - Up to 50 inputs in one generation Feed your product, your creator, and your style references into a single run. UGC marketing will never be the same. Seedance 2.5 coming soon to Higgsfield.

Adil Alimzhanov

11,569 次观看 • 1 个月前

You can create an entire AI influencer, with lore, wardrobe, a color palette, camera style, and reusable seeds, from a single Claude Fable 5 prompt. 🧵Here's the exact process to build one in Venice:

You can create an entire AI influencer, with lore, wardrobe, a color palette, camera style, and reusable seeds, from a single Claude Fable 5 prompt. 🧵Here's the exact process to build one in Venice:

Venice

19,763 次观看 • 1 个月前