LogoThread Easy
  • Explore
  • Thread Compose
LogoThread Easy

Your All-in-One Twitter Thread Companion

© 2025 Thread Easy All Rights Reserved.

Explore

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splatting

Contributions:
• We introduce the 3D Gaussian Splatting representation to the classical computer graphics problem of animating humans in 3D environments.

• We demonstrate that our framework can be used for geometry-consistent free viewpoint rendering of monocular videos edited with new animated humans.

• We introduce a novel Gaussian-aligned motion module for motion synthesis in scenes represented as 3D Gaussians.

• We introduce a human scene Gaussian refinement optimization for the correct placement of human Gaussians in scenes represented using 3DGS, leading to better contact and interactions.

AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splatting Contributions: • We introduce the 3D Gaussian Splatting representation to the classical computer graphics problem of animating humans in 3D environments. • We demonstrate that our framework can be used for geometry-consistent free viewpoint rendering of monocular videos edited with new animated humans. • We introduce a novel Gaussian-aligned motion module for motion synthesis in scenes represented as 3D Gaussians. • We introduce a human scene Gaussian refinement optimization for the correct placement of human Gaussians in scenes represented using 3DGS, leading to better contact and interactions.

Paper: https://t.co/tTZaVVvUbv

avatar for MrNeRF
MrNeRF
Fri Nov 14 07:38:39
Paper: https://t.co/MXLLZ0jzG7
Project: https://t.co/xxWzCSorHS
Code: https://t.co/50yINVq1m1

Paper: https://t.co/MXLLZ0jzG7 Project: https://t.co/xxWzCSorHS Code: https://t.co/50yINVq1m1

Founder and CEO of https://t.co/5MjtfpwEU3 | Your guide to radiance fields | Host of the podcast @ViewDependent | FTP: 279 | discord: https://t.co/lrl64WGvlD

avatar for MrNeRF
MrNeRF
Wed Nov 12 07:43:51
SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering

Contributions:
1. We propose SkelSplat, a novel framework for multi-view 3D human pose estimation, leveraging differentiable Gaussian rendering for view fusion.

2. We adapt Gaussian Splatting, primarily used for dense scene modeling, to skeleton-based 3D pose estimation.

3. We modify the original Gaussian Splatting rendering function to encode human joints using a one-hot representation, enabling pose-specific optimization.

4. We demonstrate that SkelSplat achieves accurate 3D pose estimation under challenging occlusions and varying camera setups, without requiring retraining or fine-tuning.

SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering Contributions: 1. We propose SkelSplat, a novel framework for multi-view 3D human pose estimation, leveraging differentiable Gaussian rendering for view fusion. 2. We adapt Gaussian Splatting, primarily used for dense scene modeling, to skeleton-based 3D pose estimation. 3. We modify the original Gaussian Splatting rendering function to encode human joints using a one-hot representation, enabling pose-specific optimization. 4. We demonstrate that SkelSplat achieves accurate 3D pose estimation under challenging occlusions and varying camera setups, without requiring retraining or fine-tuning.

Paper: https://t.co/MXLLZ0jzG7 Project: https://t.co/xxWzCSorHS Code: https://t.co/50yINVq1m1

avatar for MrNeRF
MrNeRF
Wed Nov 12 07:43:34
RT @DSkaale: BIG NEWS: Introducing SDF-Splats! 🚨
I just solved one of the biggest problems in 3D Gaussian Splatting: GAPS & HOLES! 🕳️❌

My…

RT @DSkaale: BIG NEWS: Introducing SDF-Splats! 🚨 I just solved one of the biggest problems in 3D Gaussian Splatting: GAPS & HOLES! 🕳️❌ My…

Founder and CEO of https://t.co/5MjtfpwEU3 | Your guide to radiance fields | Host of the podcast @ViewDependent | FTP: 279 | discord: https://t.co/lrl64WGvlD

avatar for MrNeRF
MrNeRF
Tue Nov 11 22:14:00
RT @janusch_patas: First Corporate Sponsor: Core11 GmbH Supports LichtFeld Studio!

Today marks an exciting milestone for LichtFeld Studio:…

RT @janusch_patas: First Corporate Sponsor: Core11 GmbH Supports LichtFeld Studio! Today marks an exciting milestone for LichtFeld Studio:…

Founder and CEO of https://t.co/5MjtfpwEU3 | Your guide to radiance fields | Host of the podcast @ViewDependent | FTP: 279 | discord: https://t.co/lrl64WGvlD

avatar for MrNeRF
MrNeRF
Tue Nov 11 16:01:43
ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives

TL;DR:
"ConeGS replaces cloning-based densification with a novel method that generates pixel-cone-sized primitives in regions of high image-space error. By improving placement and removing reliance on existing scene structure—thanks to a flexible iNGP-based exploration—it achieves higher reconstruction quality than baselines using the same number of primitives."

Contributions:
• A densification strategy that places new Gaussians in regions of high photometric error in image space, guided by depth estimates from an iNGP-based geometric proxy.

• An approach that determines the size of new Gaussians from the viewing cones of the pixels from which they are generated.

• An improved opacity penalty that promptly removes low-opacity Gaussians, combined with a budgeting strategy that balances scene complexity and primitive count.

ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives TL;DR: "ConeGS replaces cloning-based densification with a novel method that generates pixel-cone-sized primitives in regions of high image-space error. By improving placement and removing reliance on existing scene structure—thanks to a flexible iNGP-based exploration—it achieves higher reconstruction quality than baselines using the same number of primitives." Contributions: • A densification strategy that places new Gaussians in regions of high photometric error in image space, guided by depth estimates from an iNGP-based geometric proxy. • An approach that determines the size of new Gaussians from the viewing cones of the pixels from which they are generated. • An improved opacity penalty that promptly removes low-opacity Gaussians, combined with a budgeting strategy that balances scene complexity and primitive count.

Paper: https://t.co/bXah0hRKW5 Project: https://t.co/jngGBkvwAv

avatar for MrNeRF
MrNeRF
Tue Nov 11 08:00:54
  • Previous
  • 1
  • 2
  • 3
  • More pages
  • 14
  • 15
  • Next