Andrea Tagliasacchi's banner
Andrea Tagliasacchi's profile picture

Andrea Tagliasacchi

@taiyasaki • 17,346 subscribers

Principal Scientist @ Wayve, Associate Professor @ SFU (research chair), Associate Professor @ UofT (status only)

Shorts

📢📢📢introducing 𝐏𝐨𝐰𝐞𝐫 𝐅𝐨𝐚𝐦 A 3D representation that can be ray traced or rasterized in real time, with NO COMPROMISE in quality. - Project: - arXiv: Rasterized at 3DGS-class FPS Ray traced at Radiant Foam speeds

📢📢📢introducing 𝐏𝐨𝐰𝐞𝐫 𝐅𝐨𝐚𝐦 A 3D representation that can be ray traced or rasterized in real time, with NO COMPROMISE in quality. - Project: - arXiv: Rasterized at 3DGS-class FPS Ray traced at Radiant Foam speeds

98,503 Aufrufe

📢📢📢 𝐒𝐩𝐡𝐞𝐫𝐢𝐜𝐚𝐥 𝐕𝐨𝐫𝐨𝐧𝐨𝐢: directional appearance as a differentiable partition of the sphere – Project: – Paper: – Colab: Project led by 𝐅𝐫𝐚𝐧𝐜𝐞𝐬𝐜𝐨 𝐝𝐢 𝐒𝐚𝐫𝐢𝐨 (graduating!)

📢📢📢 𝐒𝐩𝐡𝐞𝐫𝐢𝐜𝐚𝐥 𝐕𝐨𝐫𝐨𝐧𝐨𝐢: directional appearance as a differentiable partition of the sphere – Project: – Paper: – Colab: Project led by 𝐅𝐫𝐚𝐧𝐜𝐞𝐬𝐜𝐨 𝐝𝐢 𝐒𝐚𝐫𝐢𝐨 (graduating!)

136,305 Aufrufe

📢📢📢 𝐋𝐚𝐠𝐫𝐚𝐧𝐠𝐢𝐚𝐧 𝐇𝐚𝐬𝐡𝐢𝐧𝐠 𝐟𝐨𝐫 𝐂𝐨𝐦𝐩𝐫𝐞𝐬𝐬𝐞𝐝 𝐍𝐞𝐮𝐫𝐚𝐥 𝐅𝐢𝐞𝐥𝐝 𝐑𝐞𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧𝐬 at #ECCV2024 Project led by: Shrisudhan Govindarajan (Shrisudhan Govindarajan) and Zeno Sambugaro (Zeno Sambugaro)

📢📢📢 𝐋𝐚𝐠𝐫𝐚𝐧𝐠𝐢𝐚𝐧 𝐇𝐚𝐬𝐡𝐢𝐧𝐠 𝐟𝐨𝐫 𝐂𝐨𝐦𝐩𝐫𝐞𝐬𝐬𝐞𝐝 𝐍𝐞𝐮𝐫𝐚𝐥 𝐅𝐢𝐞𝐥𝐝 𝐑𝐞𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧𝐬 at #ECCV2024 Project led by: Shrisudhan Govindarajan (Shrisudhan Govindarajan) and Zeno Sambugaro (Zeno Sambugaro)

48,546 Aufrufe

📢📢📢 Today I'll be giving a talk at the #CVPR2024 workshop on "Learning 3D with Multi-View Supervision" See you at 16:20 in Summit 331 Get a preview of the upcoming "3D Gaussian Splatting as Markov Chain Monte Carlo"

📢📢📢 Today I'll be giving a talk at the #CVPR2024 workshop on "Learning 3D with Multi-View Supervision" See you at 16:20 in Summit 331 Get a preview of the upcoming "3D Gaussian Splatting as Markov Chain Monte Carlo"

47,178 Aufrufe

📢📢📢 NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization #3DV2025 TL;DR: neural reconstruction with a simpler architecture (no linear systems to solve), and up to 3x speedup vs. voxel-based methods!

📢📢📢 NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization #3DV2025 TL;DR: neural reconstruction with a simpler architecture (no linear systems to solve), and up to 3x speedup vs. voxel-based methods!

16,962 Aufrufe

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

📢📢📢 "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing", a mesh-based 3D represention. Co-lead by my PhD students Shrisudhan Govindarajan and Daniel Rebain, and w/ Kwang Moo Yi
0:37
taiyasaki's profile picture

📢📢📢 "𝐑𝐚𝐝𝐢𝐚𝐧𝐭 𝐅𝐨𝐚𝐦: Real-Time Differentiable Ray Tracing", a mesh-based 3D represention. Co-lead by my PhD students Shrisudhan Govindarajan and Daniel Rebain, and w/ Kwang Moo Yi

Andrea Tagliasacchi

115,169 Aufrufe • vor 1 Jahr

📢📢📢 𝐓𝐫𝐢𝐚𝐧𝐠𝐥𝐞 𝐒𝐩𝐥𝐚𝐭𝐭𝐢𝐧𝐠+: 𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐛𝐥𝐞 𝐑𝐞𝐧𝐝𝐞𝐫𝐢𝐧𝐠 𝐰𝐢𝐭𝐡 𝐎𝐩𝐚𝐪𝐮𝐞 𝐓𝐫𝐢𝐚𝐧𝐠𝐥𝐞𝐬. – Project: – ArXiv: – ⚠️Code released on October 8th
0:58
taiyasaki's profile picture

📢📢📢 𝐓𝐫𝐢𝐚𝐧𝐠𝐥𝐞 𝐒𝐩𝐥𝐚𝐭𝐭𝐢𝐧𝐠+: 𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐛𝐥𝐞 𝐑𝐞𝐧𝐝𝐞𝐫𝐢𝐧𝐠 𝐰𝐢𝐭𝐡 𝐎𝐩𝐚𝐪𝐮𝐞 𝐓𝐫𝐢𝐚𝐧𝐠𝐥𝐞𝐬. – Project: – ArXiv: – ⚠️Code released on October 8th

Andrea Tagliasacchi

52,875 Aufrufe • vor 1 Jahr

📢📢📢 thrilled to announce "𝟒𝐃-𝐟𝐲: 𝐓𝐞𝐱𝐭-𝐭𝐨-𝟒𝐃 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐔𝐬𝐢𝐧𝐠 𝐇𝐲𝐛𝐫𝐢𝐝 𝐒𝐜𝐨𝐫𝐞 𝐃𝐢𝐬𝐭𝐢𝐥𝐥𝐚𝐭𝐢𝐨𝐧 𝐒𝐚𝐦𝐩𝐥𝐢𝐧𝐠" Way to start Sherwin Bahmani 🎉 PhD co-advised with David Lindell at #UofT.
0:53
taiyasaki's profile picture

📢📢📢 thrilled to announce "𝟒𝐃-𝐟𝐲: 𝐓𝐞𝐱𝐭-𝐭𝐨-𝟒𝐃 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐔𝐬𝐢𝐧𝐠 𝐇𝐲𝐛𝐫𝐢𝐝 𝐒𝐜𝐨𝐫𝐞 𝐃𝐢𝐬𝐭𝐢𝐥𝐥𝐚𝐭𝐢𝐨𝐧 𝐒𝐚𝐦𝐩𝐥𝐢𝐧𝐠" Way to start Sherwin Bahmani 🎉 PhD co-advised with David Lindell at #UofT.

Andrea Tagliasacchi

74,687 Aufrufe • vor 2 Jahren

📢📢📢 Introducing "𝐁𝐚𝐲𝐞𝐬' 𝐑𝐚𝐲𝐬: Uncertainty Quantification for Neural Radiance Fields" TL;DR: 𝐜𝐚𝐧 𝐈 "𝐭𝐫𝐮𝐬𝐭" 𝐦𝐲 𝐍𝐞𝐑𝐅 𝐚𝐭 𝐩𝐨𝐬𝐢𝐭𝐢𝐨𝐧 𝐱? with Lily Goli , @sellan_s, Cody Reading, Alec Jacobson.
0:32
taiyasaki's profile picture

📢📢📢 Introducing "𝐁𝐚𝐲𝐞𝐬' 𝐑𝐚𝐲𝐬: Uncertainty Quantification for Neural Radiance Fields" TL;DR: 𝐜𝐚𝐧 𝐈 "𝐭𝐫𝐮𝐬𝐭" 𝐦𝐲 𝐍𝐞𝐑𝐅 𝐚𝐭 𝐩𝐨𝐬𝐢𝐭𝐢𝐨𝐧 𝐱? with Lily Goli , @sellan_s, Cody Reading, Alec Jacobson.

Andrea Tagliasacchi

77,876 Aufrufe • vor 3 Jahren

📢📢📢 𝐀𝐂𝟑𝐃: 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
taiyasaki's profile picture

📢📢📢 𝐀𝐂𝟑𝐃: 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

23,088 Aufrufe • vor 1 Jahr

📢📢📢 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. 🧵👇
0:34
taiyasaki's profile picture

📢📢📢 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. 🧵👇

Andrea Tagliasacchi

18,648 Aufrufe • vor 1 Jahr

📢📢📢 𝐀𝐜𝐜𝐞𝐥𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐍𝐞𝐮𝐫𝐚𝐥 𝐅𝐢𝐞𝐥𝐝 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐯𝐢𝐚 𝐒𝐨𝐟𝐭 𝐌𝐢𝐧𝐢𝐧𝐠 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
taiyasaki's profile picture

📢📢📢 𝐀𝐜𝐜𝐞𝐥𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐍𝐞𝐮𝐫𝐚𝐥 𝐅𝐢𝐞𝐥𝐝 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐯𝐢𝐚 𝐒𝐨𝐟𝐭 𝐌𝐢𝐧𝐢𝐧𝐠 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

21,828 Aufrufe • vor 2 Jahren

📢📢📢 TC4D: Trajectory-Conditioned Text-to-4D Generation Homepage: Lead by Sherwin Bahmani, with collaborators Xian Liu Yifan Wang Ivan Skorokhodov Victor Rong Ziwei Liu Xihui Liu Jeong Joon Park Sergey Tulyakov Gordon Wetzstein Andrea Tagliasacchi @CVPR David Lindell
0:51
taiyasaki's profile picture

📢📢📢 TC4D: Trajectory-Conditioned Text-to-4D Generation Homepage: Lead by Sherwin Bahmani, with collaborators Xian Liu Yifan Wang Ivan Skorokhodov Victor Rong Ziwei Liu Xihui Liu Jeong Joon Park Sergey Tulyakov Gordon Wetzstein Andrea Tagliasacchi @CVPR David Lindell

Andrea Tagliasacchi @CVPR

16,976 Aufrufe • vor 2 Jahren

Keine weiteren Inhalte verfügbar