Loading video...

Video Failed to Load

Go Home

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข Introducing "๐๐š๐ฒ๐ž๐ฌ' ๐‘๐š๐ฒ๐ฌ: Uncertainty Quantification for Neural Radiance Fields" TL;DR: ๐œ๐š๐ง ๐ˆ "๐ญ๐ซ๐ฎ๐ฌ๐ญ" ๐ฆ๐ฒ ๐๐ž๐‘๐… ๐š๐ญ ๐ฉ๐จ๐ฌ๐ข๐ญ๐ข๐จ๐ง ๐ฑ? with Lily Goli , @sellan_s, Cody Reading, Alec Jacobson.

taiyasaki's profile picture

Andrea Tagliasacchi

16,961 subscribers

77,876 views โ€ข 3 years ago โ€ขvia X (Twitter)

LIVE

Anya Rossiโ€ข Live Now

Private livecam show

3 Comments

Samarth Sinha's profile picture
Samarth Sinha3 years ago

@lily_goli @sellan_s @code_red7777 @_AlecJacobson Looks very cool! Congrats @lily_goli !

Marvin Schmitt ๐Ÿ‘‰๐Ÿฆ‹'s profile picture
Marvin Schmitt ๐Ÿ‘‰๐Ÿฆ‹3 years ago

@lily_goli @sellan_s @code_red7777 @_AlecJacobson Nice! Whatโ€™s the computational overhead compared to vanilla NeRFs without the Bayesian UQ component? Does it still work in real-time on reasonable hardware?

Andrea Tagliasacchi ๐Ÿ‡จ๐Ÿ‡ฆ's profile picture
Andrea Tagliasacchi ๐Ÿ‡จ๐Ÿ‡ฆ3 years ago

@lily_goli @sellan_s @code_red7777 @_AlecJacobson there's no overhead at rendering time

Related Videos

๐Ÿ“ขPanoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: Yawar Siddiqui
0:44

๐Ÿ“ขPanoptic Lifting for 3D Scene Understanding with Neural Fields #CVPR23 highlight! Given only posed RGB images of a scene, we optimize a panoptic radiance field representing color, depth, semantics, and instances at any point in space. Vid: Yawar Siddiqui

Matthias Niessner

29,935 views โ€ข 3 years ago

๐Ÿ“ขIntroducing ArkRegex๐Ÿ“ข a drop in replacement for new RegExp() with types โฌ‡๏ธ
0:32

๐Ÿ“ขIntroducing ArkRegex๐Ÿ“ข a drop in replacement for new RegExp() with types โฌ‡๏ธ

ArkType

733,221 views โ€ข 10 months ago

(1/2) ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขNeRSemble #SIGGRAPH'23! We reconstruct dynamic radiance fields for high-quality novel view synthesis of human heads. Key is a deformation field and an ensemble of multi-resolution hash encodings to model coarse & fine-scale deformations.
0:35

(1/2) ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขNeRSemble #SIGGRAPH'23! We reconstruct dynamic radiance fields for high-quality novel view synthesis of human heads. Key is a deformation field and an ensemble of multi-resolution hash encodings to model coarse & fine-scale deformations.

Matthias Niessner

69,702 views โ€ข 3 years ago

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข ๐€๐œ๐œ๐ž๐ฅ๐ž๐ซ๐š๐ญ๐ข๐ง๐  ๐๐ž๐ฎ๐ซ๐š๐ฅ ๐…๐ข๐ž๐ฅ๐ ๐“๐ซ๐š๐ข๐ง๐ข๐ง๐  ๐ฏ๐ข๐š ๐’๐จ๐Ÿ๐ญ ๐Œ๐ข๐ง๐ข๐ง๐  by Shakiba Kheradmand et al. TL;DR: importance sampling for accelerating your novel view synthesis workloads (...yes, it should also work for 3DGS)
0:35

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข ๐€๐œ๐œ๐ž๐ฅ๐ž๐ซ๐š๐ญ๐ข๐ง๐  ๐๐ž๐ฎ๐ซ๐š๐ฅ ๐…๐ข๐ž๐ฅ๐ ๐“๐ซ๐š๐ข๐ง๐ข๐ง๐  ๐ฏ๐ข๐š ๐’๐จ๐Ÿ๐ญ ๐Œ๐ข๐ง๐ข๐ง๐  by Shakiba Kheradmand et al. TL;DR: importance sampling for accelerating your novel view synthesis workloads (...yes, it should also work for 3DGS)

Andrea Tagliasacchi ๐Ÿ‡จ๐Ÿ‡ฆ

21,810 views โ€ข 2 years ago

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข ๐€๐‚๐Ÿ‘๐ƒ: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers TL;DR: for 3D camera control in generative video, it really helps knowing *which* part of your model you should mess with Internship by Sherwin Bahmani at Snap
0:40

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข ๐€๐‚๐Ÿ‘๐ƒ: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers TL;DR: for 3D camera control in generative video, it really helps knowing *which* part of your model you should mess with Internship by Sherwin Bahmani at Snap

Andrea Tagliasacchi ๐Ÿ‡จ๐Ÿ‡ฆโ†’โœˆ๏ธโ†’๐Ÿ‡บ๐Ÿ‡ฒ (@CVPR)

23,040 views โ€ข 1 year ago

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข Information On How To Use Shazam Preparation for the #FLOWER song of #JISOO's #ME album Shazam with Chrome extension from PC ;
1:21

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข Information On How To Use Shazam Preparation for the #FLOWER song of #JISOO's #ME album Shazam with Chrome extension from PC ;

JISOO STREAMING

70,420 views โ€ข 3 years ago

NOAH๐Ÿ“ข ON๐Ÿ“ข HIS๐Ÿ“ข HANDS๐Ÿ“ข AND๐Ÿ“ข KNEES๐Ÿ“ข FOR๐Ÿ“ข DETHRONE๐Ÿ“ข
0:31

NOAH๐Ÿ“ข ON๐Ÿ“ข HIS๐Ÿ“ข HANDS๐Ÿ“ข AND๐Ÿ“ข KNEES๐Ÿ“ข FOR๐Ÿ“ข DETHRONE๐Ÿ“ข

๐ฌ๐ฉ๐ž๐œ๐ญ๐ž๐ซ ๐ฒ๐š๐ง๐š ๊™จ

27,013 views โ€ข 6 months ago

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข RoMo: Robust Motion Segmentation Improves Structure from Motion TL;DR: boost your SfM pipeline on dynamic scenes. We use epipolar cues + SAMv2 features to find robust masks for moving objects in a zero-shot manner. ๐Ÿงต๐Ÿ‘‡
0:34

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข RoMo: Robust Motion Segmentation Improves Structure from Motion TL;DR: boost your SfM pipeline on dynamic scenes. We use epipolar cues + SAMv2 features to find robust masks for moving objects in a zero-shot manner. ๐Ÿงต๐Ÿ‘‡

Andrea Tagliasacchi @CVPR

18,603 views โ€ข 1 year ago

Who deyyyyyy๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข
1:00

Who deyyyyyy๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข

UNUSUALPHYNA๐ŸŽ™(phynix๐Ÿ”ฅ)

767,036 views โ€ข 3 years ago

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขData release: high-res, multi-view, OLAT face recordings ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข We captured individuals in our custom light stage with 16 high-end, global shutter cameras (72 fps) and 40 LED modules, totaling 2.8M precisely calibrated frames. We us the data for BecomingLit (#NeurIPS2025): intrinsically decomposed Gaussian avatars, enabling photorealistic and real-time relighting via hybrid neural shading. Code & Data: Great work by Jonathan Schmidt, Simon Giebenhain
0:31

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขData release: high-res, multi-view, OLAT face recordings ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข We captured individuals in our custom light stage with 16 high-end, global shutter cameras (72 fps) and 40 LED modules, totaling 2.8M precisely calibrated frames. We us the data for BecomingLit (#NeurIPS2025): intrinsically decomposed Gaussian avatars, enabling photorealistic and real-time relighting via hybrid neural shading. Code & Data: Great work by Jonathan Schmidt, Simon Giebenhain

Matthias Niessner

19,515 views โ€ข 7 months ago

โ€ฆpack it up ๐Ÿ˜ญ โ€œON ALL LEVELS ฬถEฬถXฬถCฬถEฬถPฬถTฬถ ฬถPฬถHฬถYฬถSฬถIฬถCฬถAฬถLฬถ, I AM A WOLF ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขโ€ #plave #eunho #ํ”Œ๋ ˆ์ด๋ธŒ #์€ํ˜ธ
0:25

โ€ฆpack it up ๐Ÿ˜ญ โ€œON ALL LEVELS ฬถEฬถXฬถCฬถEฬถPฬถTฬถ ฬถPฬถHฬถYฬถSฬถIฬถCฬถAฬถLฬถ, I AM A WOLF ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ขโ€ #plave #eunho #ํ”Œ๋ ˆ์ด๋ธŒ #์€ํ˜ธ

plavememespls

12,736 views โ€ข 3 months ago

๐Ÿ˜ˆ๐ŸคŸ๐Ÿฝ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข
0:38

๐Ÿ˜ˆ๐ŸคŸ๐Ÿฝ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข

FMS World Series

82,289 views โ€ข 2 years ago

LOUDER FOR THE PEOPLE AT THE BACK!!! ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข
1:38

LOUDER FOR THE PEOPLE AT THE BACK!!! ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข

Kapuso Crave

359,077 views โ€ข 1 year ago

HAIKYUU LIVE READING "FUTURE CAPTAIN" ๐Ÿ“ข
2:12

HAIKYUU LIVE READING "FUTURE CAPTAIN" ๐Ÿ“ข

xhatosanแฐ.แŸ

303,603 views โ€ข 1 year ago

๐Ÿ“ŒBu gece itibarฤฑ ile girmiลŸ olduฤŸumuz Zilhiccenin ilk 10 gรผnรผnรผn รถnemiโ— ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข
1:32

๐Ÿ“ŒBu gece itibarฤฑ ile girmiลŸ olduฤŸumuz Zilhiccenin ilk 10 gรผnรผnรผn รถnemiโ— ๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข

Tarik~i Mahmudiyye

26,108 views โ€ข 1 year ago

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข
0:47

๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข๐Ÿ“ข

ร‰quipe Cycliste Groupama-FDJ United

262,094 views โ€ข 3 years ago