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.

📢 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

9,774 subscribers

13,438 views • 1 year ago •via X (Twitter)

Science & Technology Education Arts

Anya Rossi• Live Now

Private livecam show

3 Comments

Out of AI1 year ago

@chandan__yes @liuyuehcheng amazing work, that it's going to help us with our research as well.

Λbstract2 years ago

RT @InstaMAT_io: 👀 Are you looking for an alternative to Adobe Substance tools? Do not miss out on InstaMAT from killer node-based material…

Anne1 year ago

@chandan__yes @liuyuehcheng Incredible!

Related Videos

Excited to announce ScanNet++ v2!🎉 Chandan Yeshwanth and Yueh-Cheng Liu have been working tirelessly to bring: 🔹1006 high-fidelity 3D scans 🔹+ DSLR & iPhone captures 🔹+ rich semantics Elevating 3D scene understanding to the next level!🚀 w/ Matthias Niessner

Excited to announce ScanNet++ v2!🎉 Chandan Yeshwanth and Yueh-Cheng Liu have been working tirelessly to bring: 🔹1006 high-fidelity 3D scans 🔹+ DSLR & iPhone captures 🔹+ rich semantics Elevating 3D scene understanding to the next level!🚀 w/ Matthias Niessner

Angela Dai

47,629 views • 1 year 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

10,289 views • 3 years 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

12,635 views • 1 year ago

📢 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

27,344 views • 1 year ago

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians Contributions: • We propose SuperGSeg: a 3D segmentation method with neural Gaussians, designed to learn hierarchical instance segmentation features from 2D foundation models. • We introduce the concept of Super-Gaussian, a novel representation that integrates hierarchical instance segmentation features, enabling the embedding of high-dimensional language features. This approach addresses previously unfeasible challenges in representing complex scenes with rich semantic details. • Extensive experiments on the LERF-OVS and ScanNet datasets demonstrate the effectiveness of the proposed method, achieving significant improvements in open-vocabulary 3D object-level and scene-level semantic segmentation. It shows particular strength in capturing fine-grained scene details and dense pixel semantic segmentation tasks for the first time.

SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians Contributions: • We propose SuperGSeg: a 3D segmentation method with neural Gaussians, designed to learn hierarchical instance segmentation features from 2D foundation models. • We introduce the concept of Super-Gaussian, a novel representation that integrates hierarchical instance segmentation features, enabling the embedding of high-dimensional language features. This approach addresses previously unfeasible challenges in representing complex scenes with rich semantic details. • Extensive experiments on the LERF-OVS and ScanNet datasets demonstrate the effectiveness of the proposed method, achieving significant improvements in open-vocabulary 3D object-level and scene-level semantic segmentation. It shows particular strength in capturing fine-grained scene details and dense pixel semantic segmentation tasks for the first time.

MrNeRF

13,594 views • 1 year ago

📢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:

📢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

18,017 views • 7 months ago

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

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

AK

304,708 views • 3 years ago

Mask3D 🎭 is now at #ICRA2023, great work Jonas Schult! We use Mask Transformers for 3D Instance Segmentation on Point Clouds ~ 🥇 on ScanNet 📰Paper: 🛠️Project: 👨‍💻Code: @Pandoro89 Or Litany Siyu Tang @VLG-ETHZ

Mask3D 🎭 is now at #ICRA2023, great work Jonas Schult! We use Mask Transformers for 3D Instance Segmentation on Point Clouds ~ 🥇 on ScanNet 📰Paper: 🛠️Project: 👨‍💻Code: @Pandoro89 Or Litany Siyu Tang @VLG-ETHZ

Francis Engelmann

29,179 views • 3 years ago

Introducing the Superform V2 Web App, live in Open Access 🥳 🔹 Access using a wallet, social account or passkey 🔹 View your unified portfolio 🔹 Earn more on your assets w/ SuperVaults 🔹 Bridge, swap & reallocate across 7 chains in a tx Earn more ➡️

Introducing the Superform V2 Web App, live in Open Access 🥳 🔹 Access using a wallet, social account or passkey 🔹 View your unified portfolio 🔹 Earn more on your assets w/ SuperVaults 🔹 Bridge, swap & reallocate across 7 chains in a tx Earn more ➡️

Superform

78,986 views • 1 year ago

📢📢📢 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)

📢📢📢 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 views • 2 years ago

The biggest winner of the State of Play was Lords of the Fallen 2 in my opinion. 🔹Launching on steam along with other platforms 🔹Soulslike supply chain is really DRY right now, so they along with Mortal Shell are 🔥 🔹The art & env in the showcase looked incredible. 🔹Hands on soon confirmed by their CEO 🔹And to top it off they released untouched gameplay of the game that basically looks and feels like Khazan and Sekiro level.

The biggest winner of the State of Play was Lords of the Fallen 2 in my opinion. 🔹Launching on steam along with other platforms 🔹Soulslike supply chain is really DRY right now, so they along with Mortal Shell are 🔥 🔹The art & env in the showcase looked incredible. 🔹Hands on soon confirmed by their CEO 🔹And to top it off they released untouched gameplay of the game that basically looks and feels like Khazan and Sekiro level.

SpawnYaard 🎮

117,494 views • 5 months ago

🚀 Missed our $35,000 CBT event? No worries! 🚀 More exclusive events are coming, including 🌟Somnis Open Beta!🌟 🔹 Sign up now and secure your spot 👉 🔹 Join our Discord for event announcements 👉 🔹 Earn rewards with our POP Quest Collections 👉 🔹 Check out The Red One: Occultation Trailer 👉 Get ready for an incredible journey and don’t miss out on our another rewarding events to come! 🌠

🚀 Missed our $35,000 CBT event? No worries! 🚀 More exclusive events are coming, including 🌟Somnis Open Beta!🌟 🔹 Sign up now and secure your spot 👉 🔹 Join our Discord for event announcements 👉 🔹 Earn rewards with our POP Quest Collections 👉 🔹 Check out The Red One: Occultation Trailer 👉 Get ready for an incredible journey and don’t miss out on our another rewarding events to come! 🌠

OVERTAKE

85,889 views • 2 years ago

RobotArena is live today! Led by @sumo43_, RobotArena is an ELO-based 🤖 Robot-Action Model benchmark that allows you to test models directly in your browser. Check it out here: Special thanks to HIVE Digital Technologies for their compute support!

RobotArena is live today! Led by @sumo43_, RobotArena is an ELO-based 🤖 Robot-Action Model benchmark that allows you to test models directly in your browser. Check it out here: Special thanks to HIVE Digital Technologies for their compute support!

skunkworks

34,446 views • 2 years ago

Incline - Next-generation granular re-synthesis instrument. Driven by state-of-the-art analysis, segmentation, and a granular engine, Incline reaches new heights on the sonic terrain.

Incline - Next-generation granular re-synthesis instrument. Driven by state-of-the-art analysis, segmentation, and a granular engine, Incline reaches new heights on the sonic terrain.

Richard Devine

21,415 views • 8 months ago

🤯 Mind-blowing! Just witnessed the magic of #Palworld! 🔥 Check out the incredible Rodin Gen-1 🤖 transforming images into 3D models in just 10 seconds! 🚀 #CG #3D #game #GenerativeAI #GenAI #diffusion

🤯 Mind-blowing! Just witnessed the magic of #Palworld! 🔥 Check out the incredible Rodin Gen-1 🤖 transforming images into 3D models in just 10 seconds! 🚀 #CG #3D #game #GenerativeAI #GenAI #diffusion

Hyper3D by Deemos

114,796 views • 2 years ago

We are introducing Hunyuan3D-Part: an open-source part-level 3D shape generation model that outperforms all existing open and close-source models. Highlights: 🔹P3-SAM: The industry's first native 3D part segmentation model. 🔹X-Part: A part generation model that achieves state-of-the-art results in controllability and shape quality. Key-features: 1️⃣Eliminates the use of 2D SAM during training, relying solely on a large-scale dataset with 3.7 million shapes and clean part annotations. 2️⃣Introduces a new automated segmentation pipeline in 3D without user intervention. 3️⃣Implements a diffusion-based part decomposition pipeline utilizing both geometry and semantic clues. Code: Weights: Tech reports: 🔸P3-SAM： → Paper: → Project page: 🔸X-Part： → Paper: → Project page: Try it now： → (Light version) Hugging Face demo: → (Full version) Hunyuan3D Studio:

We are introducing Hunyuan3D-Part: an open-source part-level 3D shape generation model that outperforms all existing open and close-source models. Highlights: 🔹P3-SAM: The industry's first native 3D part segmentation model. 🔹X-Part: A part generation model that achieves state-of-the-art results in controllability and shape quality. Key-features: 1️⃣Eliminates the use of 2D SAM during training, relying solely on a large-scale dataset with 3.7 million shapes and clean part annotations. 2️⃣Introduces a new automated segmentation pipeline in 3D without user intervention. 3️⃣Implements a diffusion-based part decomposition pipeline utilizing both geometry and semantic clues. Code: Weights: Tech reports: 🔸P3-SAM： → Paper: → Project page: 🔸X-Part： → Paper: → Project page: Try it now： → (Light version) Hugging Face demo: → (Full version) Hunyuan3D Studio:

Tencent Hy

72,640 views • 1 year ago

Introducing Private Mind! 🚀 Our new open-source app, built with React Native ExecuTorch, lets you run LLMs 100% locally on your device. 🔹 Explore and swap pre-exported models 🔹 Benchmark performance, speed & memory 🔹 Customize system prompts 🔹 100% offline, private & free Now available on App Store and Google Play! Links in 🧵

Introducing Private Mind! 🚀 Our new open-source app, built with React Native ExecuTorch, lets you run LLMs 100% locally on your device. 🔹 Explore and swap pre-exported models 🔹 Benchmark performance, speed & memory 🔹 Customize system prompts 🔹 100% offline, private & free Now available on App Store and Google Play! Links in 🧵

Software Mansion

21,764 views • 1 year ago

🚀 Unlock the Full Potential of Your Genuine Undead NFTs! 🧟‍♂️🔥 I just upgraded a #GenuineUndead V1 to V2 and explored all the new features! 🎉 🔹 Easy Migration Process🔹 Access High-Quality Assets🔹 Minting Your Undeadz🔹 On-Chain Engraving Make sure to follow GenuinelyUndead to join the #GenuineRising and be part of the next chapter! Watch my step-by-step guide to get started 👇

🚀 Unlock the Full Potential of Your Genuine Undead NFTs! 🧟‍♂️🔥 I just upgraded a #GenuineUndead V1 to V2 and explored all the new features! 🎉 🔹 Easy Migration Process🔹 Access High-Quality Assets🔹 Minting Your Undeadz🔹 On-Chain Engraving Make sure to follow GenuinelyUndead to join the #GenuineRising and be part of the next chapter! Watch my step-by-step guide to get started 👇

𝐌𝐀𝐈𝐒𝐎𝐍💀🤙

15,935 views • 2 years ago

In this Lovecraftian Extraction FPS you play as a scavenger that descends into the abyss 🔹Mental Power system that has players manage their psychological state 🔹Environment becomes increasingly hostile and the world distorts as runs go on 🔹Look for weapons, materials, and unique resources to extract 🔹Fight monstrous creatures and other players 🔹Upgrade your Bio-Arm using resources 🔹Upgrade your hideout to expand production facilities 🔹First closed alpha test is Sep 4 - Sep 8 🎮"Waste The Fallen"

In this Lovecraftian Extraction FPS you play as a scavenger that descends into the abyss 🔹Mental Power system that has players manage their psychological state 🔹Environment becomes increasingly hostile and the world distorts as runs go on 🔹Look for weapons, materials, and unique resources to extract 🔹Fight monstrous creatures and other players 🔹Upgrade your Bio-Arm using resources 🔹Upgrade your hideout to expand production facilities 🔹First closed alpha test is Sep 4 - Sep 8 🎮"Waste The Fallen"

Game Hunter

29,962 views • 3 months ago

🚀Announcing NeRSemble 3D Head Avatar Benchmark v2 Version 2 of the NeRSemble 3D Head Avatar Benchmark systematically evaluates several aspects of 3D head avatar creation. Our goal is to drive progress toward more realistic, robust, and generalizable avatar methods. 🔬Benchmark Tasks The NeRSemble Benchmark v2 features three core challenges: - Dynamic Novel View Synthesis - Monocular FLAME-driven Avatar Creation (updated) - Single-view 3D Face Reconstruction (new) 👉Explore the online leaderboard and submission system: 🆕What's new? 1. New Task: Single-view 3D Face Reconstruction Given a single portrait image, reconstruct an accurate 3D mesh either showing the input expression or a fully neutral one. Unlike prior benchmarks, the NeRSemble benchmark emphasizes diverse and challenging facial expressions, better reflecting real scenarios. For technical details, see the Pixel3DMM paper. 2. Updated task: Monocular FLAME-driven Avatar Creation We have improved the FLAME tracking that is used for both avatar creation from the monocular videos and avatar driving on the hidden test sequences. The updated benchmark task has: - more stable torso tracking - more expressive lip closures during speech - Improved mouth tracking for challenging facial expressions We hope that these improvements to the benchmark help drive the field forward. 🏆 CVPR 2026 Workshop & Prizes The NeRSemble benchmark will be featured at the CVPR 2026 Workshop on Photo-realistic 3D Head Avatars. Participants in the new and updated tasks have the opportunity to win: - 🎁RTX 5080 GPUs (sponsored by NVIDIA) - 🎤15-minute oral presentation at the workshop ⏰ Submission Deadline - May 26, 2026 Reach out to the amazing Tobias Kirschstein and Simon Giebenhain for more details :)

Matthias Niessner

30,170 views • 7 months ago