Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

📢Diff3r: fast feed-forward 3DGS + per-scene optimization Yueh-Cheng Liu predicts optimization-ready 3DGS init end to end, computing implicit gradients via Implicit Function Theorem + Gauss-Newton approximation for fast & stable results Check it out:

Angela Dai

9,504 subscribers

17,730 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

📢 QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization Yueh-Cheng Liu learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction! Project:

📢 QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization Yueh-Cheng Liu learns 2DGS initialization, densification, and optimization priors from ScanNet++ => fast & accurate reconstruction! Project:

Angela Dai

27,295 views • 1 year ago

🚀Join the 𝐒𝐜𝐚𝐧𝐍𝐞𝐭++ 𝐂𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞 #CVPR2026 2025! Think your method can handle large-scale 3D scenes? Put it to the test: Updates: ✅ Preprocessed, undistorted DSLR images ✅ 3DGS demo: by Yueh-Cheng Liu, Chandan Yeshwanth

🚀Join the 𝐒𝐜𝐚𝐧𝐍𝐞𝐭++ 𝐂𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐞 #CVPR2026 2025! Think your method can handle large-scale 3D scenes? Put it to the test: Updates: ✅ Preprocessed, undistorted DSLR images ✅ 3DGS demo: by Yueh-Cheng Liu, Chandan Yeshwanth

Angela Dai

12,619 views • 1 year ago

DJI OSMO360 with my tool is very easy and fast for 3DGS workflow. This 3DGS took only 5 min walk for capturing whole shrine :) Let's try 3DGS ! #OSMO360 #3DGS #Metashape #Postshot #Gaussian

DJI OSMO360 with my tool is very easy and fast for 3DGS workflow. This 3DGS took only 5 min walk for capturing whole shrine :) Let's try 3DGS ! #OSMO360 #3DGS #Metashape #Postshot #Gaussian

kotohibi

45,853 views • 3 months ago

📢 ScanNet++ v2 Benchmark Release! 🏆 Test your state-of-the-art models on: 🔹 Novel View Synthesis 📸➡️🖼️ 🔹 3D Semantic & Instance Segmentation 🤖🔍🕶️ Shoutout to Chandan Yeshwanth and Yueh-Cheng Liu for their incredible work👏 🚀Check it out:

📢 ScanNet++ v2 Benchmark Release! 🏆 Test your state-of-the-art models on: 🔹 Novel View Synthesis 📸➡️🖼️ 🔹 3D Semantic & Instance Segmentation 🤖🔍🕶️ Shoutout to Chandan Yeshwanth and Yueh-Cheng Liu for their incredible work👏 🚀Check it out:

Angela Dai

13,428 views • 1 year ago

Spatial optimization has applications in nearly every field but it's underutilized. In 2026, I'm working on open source and lightning-fast tools to make spatial optimization accessible. Shown: interactively solving a "location-allocation" problem in an app with instant results.

Spatial optimization has applications in nearly every field but it's underutilized. In 2026, I'm working on open source and lightning-fast tools to make spatial optimization accessible. Shown: interactively solving a "location-allocation" problem in an app with instant results.

Kyle Walker

28,495 views • 5 months ago

Just fast forward it to the end and see Wetin this guy dey do himself 💔

Just fast forward it to the end and see Wetin this guy dey do himself 💔

Oyindamola🙄

339,136 views • 1 year ago

HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting Contributions: First, we propose Homogeneous Gaussian Splatting (HoGS), a novel method adopting homogeneous coordinates to represent positions and scales of 3DGS for realistic and real-time rendering of both near and far objects. Second, despite the ultimate simplicity of HoGS, our method achieves state-of-the-art NVS results compared to other implicit and explicit representations.

HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting Contributions: First, we propose Homogeneous Gaussian Splatting (HoGS), a novel method adopting homogeneous coordinates to represent positions and scales of 3DGS for realistic and real-time rendering of both near and far objects. Second, despite the ultimate simplicity of HoGS, our method achieves state-of-the-art NVS results compared to other implicit and explicit representations.

MrNeRF

22,978 views • 1 year ago

Dear Visitors, Please check out the [Room] Misty Villa Optimization & New Matching Furniture, [Collection Furniture] Moon Over Clouds, and other Collection Furniture Optimization in action! #IdentityV

Dear Visitors, Please check out the [Room] Misty Villa Optimization & New Matching Furniture, [Collection Furniture] Moon Over Clouds, and other Collection Furniture Optimization in action! #IdentityV

Identity V

152,842 views • 10 months ago

Looking for a challenging dataset for novel view synthesis and 3D semantics? Check out ScanNet++ at #ICCV23 (Oral)! 460+ scenes w/ 1mm laser scans, semantics, DSLR images, iPhone RGBD video Chandan Yeshwanth Yueh-Cheng Liu Matthias Niessner

Looking for a challenging dataset for novel view synthesis and 3D semantics? Check out ScanNet++ at #ICCV23 (Oral)! 460+ scenes w/ 1mm laser scans, semantics, DSLR images, iPhone RGBD video Chandan Yeshwanth Yueh-Cheng Liu Matthias Niessner

Angela Dai

10,283 views • 2 years ago

3DGS Render Addon for Blender is out! New features include: - Paint and use image textures to edit colour - Mesh to 3DGS conversion - Transformations and edits are exportable - Lot's of other boosts and little features! Link for the addon and a Quick Guide tutorial below #b3d #blender #3dgs #gaussiansplatting

3DGS Render Addon for Blender is out! New features include: - Paint and use image textures to edit colour - Mesh to 3DGS conversion - Transformations and edits are exportable - Lot's of other boosts and little features! Link for the addon and a Quick Guide tutorial below #b3d #blender #3dgs #gaussiansplatting

KIRI Engine - 3D Scanner App

19,019 views • 1 year ago

📢ScanEdit: Hierarchically-Guided Functional 3D Scan Editing Edit complex, real-world 3D scans with text -- Mohamed El Amine Boudjoghra combines LLM reasoning with geometric optimization to produce physically plausible, instruction-aligned scene edits Check it out:

📢ScanEdit: Hierarchically-Guided Functional 3D Scan Editing Edit complex, real-world 3D scans with text -- Mohamed El Amine Boudjoghra combines LLM reasoning with geometric optimization to produce physically plausible, instruction-aligned scene edits Check it out:

Angela Dai

12,985 views • 1 year ago

Okatakyie Afrifa invokes curses on all persons implicit in galamsey operations at the end of his anti galamsey protest.

Okatakyie Afrifa invokes curses on all persons implicit in galamsey operations at the end of his anti galamsey protest.

SIKAOFFICIAL🦍

222,366 views • 1 year ago

(1/2) How to use GANs for high-quality NeRF reconstruction? GANeRF proposes an adversarial rendering formulation whose gradients constrain a 3D NeRF optimization: highly-realistic & view-consistent renderings! #SIGGRAPHAsia2023

(1/2) How to use GANs for high-quality NeRF reconstruction? GANeRF proposes an adversarial rendering formulation whose gradients constrain a 3D NeRF optimization: highly-realistic & view-consistent renderings! #SIGGRAPHAsia2023

Matthias Niessner

41,705 views • 2 years ago

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! 🌍 📽️

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

30,787 views • 9 months ago

Check out 🌟Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry & Physics for Mesh-Free Simulation #CVPR2025, from Lingjie Liu’s lab at UPenn. Congrats to Chuhao Chen! Vid2Sim aims to achieve system identification by reconstructing geometry, appearance, and physical properties directly from video. It combines learned data priors with closed-loop optimization: a feed-forward predictor trained on physical prior, followed by fast refinement via Neural Jacobian and mesh-free simulation. The system delivers simulation-ready outputs in minutes, with strong generalization across objects and materials. 🏠Project page: #PhysicalAI #AIGC #CV #CG #simulation #graphics

Check out 🌟Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry & Physics for Mesh-Free Simulation #CVPR2025, from Lingjie Liu’s lab at UPenn. Congrats to Chuhao Chen! Vid2Sim aims to achieve system identification by reconstructing geometry, appearance, and physical properties directly from video. It combines learned data priors with closed-loop optimization: a feed-forward predictor trained on physical prior, followed by fast refinement via Neural Jacobian and mesh-free simulation. The system delivers simulation-ready outputs in minutes, with strong generalization across objects and materials. 🏠Project page: #PhysicalAI #AIGC #CV #CG #simulation #graphics

Zhiyang (Frank) Dou

12,393 views • 1 year ago

🔛🔛🔛🔛 Sim init Web3 Devs 🔛🔛🔛🔛 Introducing Sim Sim IDX, the end-to-end multichain indexing layer for onchain apps. ❇️ Super-Fast Backfills ❇️ Solidity-native enrichment ❇️ Zero DevOps ❇️ Streaming and historical Are you ready to change the game?

🔛🔛🔛🔛 Sim init Web3 Devs 🔛🔛🔛🔛 Introducing Sim Sim IDX, the end-to-end multichain indexing layer for onchain apps. ❇️ Super-Fast Backfills ❇️ Solidity-native enrichment ❇️ Zero DevOps ❇️ Streaming and historical Are you ready to change the game?

Dune

121,934 views • 11 months ago

Nothing wey no happen for church today, this is Pastor Eneche of the Dunamis church…just try watch till the end or just fast forward to the end 😭🧎🏻‍♂️‍➡️

Nothing wey no happen for church today, this is Pastor Eneche of the Dunamis church…just try watch till the end or just fast forward to the end 😭🧎🏻‍♂️‍➡️

Oyindamola🙄

844,943 views • 17 days ago

Normally, 3D Gaussian Splatting stops at “pretty renders”. 😎 Our 3DGS→Mesh 2.0 doesn’t stop there. 😤 We merged mesh generation into Gaussian optimization itself 🧭— predicting normals, filtering reflections✨, and forming surfaces as it trains. Result: manifold, reflection-aware mesh from pure Gaussians🚀

Normally, 3D Gaussian Splatting stops at “pretty renders”. 😎 Our 3DGS→Mesh 2.0 doesn’t stop there. 😤 We merged mesh generation into Gaussian optimization itself 🧭— predicting normals, filtering reflections✨, and forming surfaces as it trains. Result: manifold, reflection-aware mesh from pure Gaussians🚀

KIRI Engine - 3D Scanner App

40,927 views • 8 months ago

Omg Jesse schools Jessica! lol 😂! The end is priceless on this video! You could just fast forward to the end 😂😂😂😂

Omg Jesse schools Jessica! lol 😂! The end is priceless on this video! You could just fast forward to the end 😂😂😂😂

Kathleen Winchell ❤️🤍💙🇺🇸🇺🇸

107,536 views • 1 year ago

📢 We introduce PPISP, a physically plausible camera module for Gaussian Splatting that reduces floaters under varying appearance and predicts camera corrections for novel views such that they closely match what a real camera would output. #CV #3DGS

📢 We introduce PPISP, a physically plausible camera module for Gaussian Splatting that reduces floaters under varying appearance and predicts camera corrections for novel views such that they closely match what a real camera would output. #CV #3DGS

Zan Gojcic

26,092 views • 4 months ago