Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

vMAP: Vectorised Object Mapping for Neural Field SLAM abs: project page:

_akhaliq's profile picture

AK

504,101 subscribers

36,137 görüntüleme • 3 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

1 Yorum

42Papers - Trending Papers AI / ML / CS profil fotoğrafı
42Papers - Trending Papers AI / ML / CS3 yıl önce

Here's a quick summary for this paper.

Benzer Videolar

vMAP: Vectorised Object Mapping for Neural Field SLAM, new at #CVPR2023! Each object is represented by a separate MLP, optimised in parallel via vectorised training. Full info: Dyson Robotics Lab, Imperial College, Shikun Liu, Marwan Taher, Andrew Davison.
0:24

vMAP: Vectorised Object Mapping for Neural Field SLAM, new at #CVPR2023! Each object is represented by a separate MLP, optimised in parallel via vectorised training. Full info: Dyson Robotics Lab, Imperial College, Shikun Liu, Marwan Taher, Andrew Davison.

Xin Kong

23,743 görüntüleme • 3 yıl önce

Real-Time Neural Light Field on Mobile Devices abs: project page:
0:27

Real-Time Neural Light Field on Mobile Devices abs: project page:

AK

56,201 görüntüleme • 3 yıl önce

Neural Congealing: Aligning Images to a Joint Semantic Atlas abs: project page:
0:40

Neural Congealing: Aligning Images to a Joint Semantic Atlas abs: project page:

AK

51,709 görüntüleme • 3 yıl önce

Check out the Neural Graph Mapping for Dense SLAM with Efficient Loop Closure paper by Leonard Bruns, Jun Zhang, and Patric Jensfelt, visualized with Rerun. “Existing neural field-based SLAM methods typically employ a single monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a neural mapping framework which anchors lightweight neural fields to the pose graph of a sparse visual SLAM system.”
0:37

Check out the Neural Graph Mapping for Dense SLAM with Efficient Loop Closure paper by Leonard Bruns, Jun Zhang, and Patric Jensfelt, visualized with Rerun. “Existing neural field-based SLAM methods typically employ a single monolithic field as their scene representation. This prevents efficient incorporation of loop closure constraints and limits scalability. To address these shortcomings, we propose a neural mapping framework which anchors lightweight neural fields to the pose graph of a sparse visual SLAM system.”

Rerun

12,861 görüntüleme • 2 yıl önce

Word-As-Image for Semantic Typography abs: project page:
1:46

Word-As-Image for Semantic Typography abs: project page:

AK

385,996 görüntüleme • 3 yıl önce

GeoCode: Interpretable Shape Programs abs: project page:
1:08

GeoCode: Interpretable Shape Programs abs: project page:

AK

1,428,749 görüntüleme • 3 yıl önce

Single Motion Diffusion abs: project page:
2:15

Single Motion Diffusion abs: project page:

AK

72,767 görüntüleme • 3 yıl önce

MusicLM: Generating Music From Text abs: project page:
2:16

MusicLM: Generating Music From Text abs: project page:

AK

434,142 görüntüleme • 3 yıl önce

3D-aware Conditional Image Synthesis abs: project page:
0:34

3D-aware Conditional Image Synthesis abs: project page:

AK

301,457 görüntüleme • 3 yıl önce

Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion abs: project page:
1:22

Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion abs: project page:

AK

262,780 görüntüleme • 3 yıl önce

Towards Realistic Generative 3D Face Models abs: project page:
0:53

Towards Realistic Generative 3D Face Models abs: project page:

AK

48,089 görüntüleme • 3 yıl önce

ReBotNet: Fast Real-time Video Enhancement abs: project page:
0:25

ReBotNet: Fast Real-time Video Enhancement abs: project page:

AK

111,249 görüntüleme • 3 yıl önce

ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement abs: project page:
0:34

ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement abs: project page:

AK

34,949 görüntüleme • 3 yıl önce

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints project page: paper page:
3:06

Synthesia research releases HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints project page: paper page:

AK

160,700 görüntüleme • 3 yıl önce

Expressive Text-to-Image Generation with Rich Text abs: project page:
0:34

Expressive Text-to-Image Generation with Rich Text abs: project page:

AK

209,253 görüntüleme • 3 yıl önce

SLAM algorithms struggle on endoscopy videos - specularity, textureless, & dynamic near-field lighting. We introduce a Near-Field Light Bundle Adjst. loss (NFL-BA): improves performance of SOTA SLAM, e.g. MonoGS (⬆️35% in tracking, ⬆️48% in mapping). See
0:23

SLAM algorithms struggle on endoscopy videos - specularity, textureless, & dynamic near-field lighting. We introduce a Near-Field Light Bundle Adjst. loss (NFL-BA): improves performance of SOTA SLAM, e.g. MonoGS (⬆️35% in tracking, ⬆️48% in mapping). See

Roni Sengupta

19,140 görüntüleme • 1 yıl önce

Generative Novel View Synthesis with 3D-Aware Diffusion Models abs: project page:
0:24

Generative Novel View Synthesis with 3D-Aware Diffusion Models abs: project page:

AK

304,708 görüntüleme • 3 yıl önce

SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections abs: project page:
0:58

SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections abs: project page:

AK

317,619 görüntüleme • 3 yıl önce

Google announces InseRF Text-Driven Generative Object Insertion in Neural 3D Scenes paper page: InseRF generates an object in a 3D scene via a text prompt and one 2D bounding box
1:35

Google announces InseRF Text-Driven Generative Object Insertion in Neural 3D Scenes paper page: InseRF generates an object in a 3D scene via a text prompt and one 2D bounding box

AK

205,943 görüntüleme • 2 yıl önce

"near real-time method for 6-DoF tracking of an unknown object from a monocular RGBD video sequence [...] a Neural Object Field that is learned concurrently with a pose graph optimization process in order to robustly accumulate information into a consistent 3D representation"
0:53

"near real-time method for 6-DoF tracking of an unknown object from a monocular RGBD video sequence [...] a Neural Object Field that is learned concurrently with a pose graph optimization process in order to robustly accumulate information into a consistent 3D representation"

Fabien Benetou

222,906 görüntüleme • 3 yıl önce