Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

#ICLR2023 "Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction" Our Voxurf is accepted to ICLR as **spotlight** presentation, achieving higher reconstruction quality with 20x speedup. - Paper: - Code:

liuziwei7's profile picture

Ziwei Liu

13,636 subscribers

28,770 Aufrufe • vor 3 Jahren •via X (Twitter)

#ICLR2023
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

📢📢📢 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!
0:15

📢📢📢 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!

Andrea Tagliasacchi @CVPR

16,962 Aufrufe • vor 1 Jahr

DLSS 4.5 is coming to Ray Reconstruction! Massive image quality improvements for games with Ray Reconstruction 👍
0:11

DLSS 4.5 is coming to Ray Reconstruction! Massive image quality improvements for games with Ray Reconstruction 👍

Jacob Freeman

85,161 Aufrufe • vor 5 Monaten

🚀 #NVlabs #InstantSplat now supports high-quality sparse-view surface reconstruction in just seconds! 📸 Build your scene with just 3 images. It's effortless, fast, and ready for you to explore. 💻 Code is now available
0:17

🚀 #NVlabs #InstantSplat now supports high-quality sparse-view surface reconstruction in just seconds! 📸 Build your scene with just 3 images. It's effortless, fast, and ready for you to explore. 💻 Code is now available

Zhiwen(Aaron) Fan

23,090 Aufrufe • vor 1 Jahr

EDGS: Eliminating Densification for Efficient Convergence of 3DGS Contributions: • We show that initial triangulation based on 2D correspondences can replace the incremental refinement process, fundamentally changing how 3DGS models allocate resources. • Our method reduces the path each Gaussian must travel in parameter space. Careful initialization not only accelerates convergence but also guides optimization toward a convergence point corresponding to lower reconstruction error and thus higher reconstruction quality. • Our approach outperforms both speed-optimized and quality-focused state-of-the-art models while using only half the splats of standard 3DGS. By improving initialization rather than altering the optimization process, this method is compatible with other 3DGS acceleration techniques, making it a flexible enhancement to existing models.
0:15

EDGS: Eliminating Densification for Efficient Convergence of 3DGS Contributions: • We show that initial triangulation based on 2D correspondences can replace the incremental refinement process, fundamentally changing how 3DGS models allocate resources. • Our method reduces the path each Gaussian must travel in parameter space. Careful initialization not only accelerates convergence but also guides optimization toward a convergence point corresponding to lower reconstruction error and thus higher reconstruction quality. • Our approach outperforms both speed-optimized and quality-focused state-of-the-art models while using only half the splats of standard 3DGS. By improving initialization rather than altering the optimization process, this method is compatible with other 3DGS acceleration techniques, making it a flexible enhancement to existing models.

MrNeRF

125,025 Aufrufe • vor 1 Jahr

What if I told you there's a Neural 3D Reconstruction method that: * is mesh-based * 👀 renders at 120FPS 👀 * uses Neural Texture Fields NeuRas by Waabi is the new cool kid in town that nobody is paying attention to (yet), imo: 1/3
0:14

What if I told you there's a Neural 3D Reconstruction method that: * is mesh-based * 👀 renders at 120FPS 👀 * uses Neural Texture Fields NeuRas by Waabi is the new cool kid in town that nobody is paying attention to (yet), imo: 1/3

Alberto

261,830 Aufrufe • vor 3 Jahren

NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions paper page: present a novel type of neural fields that uses general radial bases for signal representation. State-of-the-art neural fields typically rely on grid-based representations for storing local neural features and N-dimensional linear kernels for interpolating features at continuous query points. The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals. Our method instead builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. To further improve the channel-wise capacity of radial basis functions, we propose to compose them with multi-frequency sinusoid functions. This technique extends a radial basis to multiple Fourier radial bases of different frequency bands without requiring extra parameters, facilitating the representation of details. Moreover, by marrying adaptive radial bases with grid-based ones, our hybrid combination inherits both adaptivity and interpolation smoothness. We carefully designed weighting schemes to let radial bases adapt to different types of signals effectively. Our experiments on 2D image and 3D signed distance field representation demonstrate the higher accuracy and compactness of our method than prior arts. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.
0:15

NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions paper page: present a novel type of neural fields that uses general radial bases for signal representation. State-of-the-art neural fields typically rely on grid-based representations for storing local neural features and N-dimensional linear kernels for interpolating features at continuous query points. The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals. Our method instead builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. To further improve the channel-wise capacity of radial basis functions, we propose to compose them with multi-frequency sinusoid functions. This technique extends a radial basis to multiple Fourier radial bases of different frequency bands without requiring extra parameters, facilitating the representation of details. Moreover, by marrying adaptive radial bases with grid-based ones, our hybrid combination inherits both adaptivity and interpolation smoothness. We carefully designed weighting schemes to let radial bases adapt to different types of signals effectively. Our experiments on 2D image and 3D signed distance field representation demonstrate the higher accuracy and compactness of our method than prior arts. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.

AK

194,523 Aufrufe • vor 3 Jahren

📢Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image📢 We directly regress neural parametric head models (NPHMs) from a single image — fast, stable, and significantly more expressive than classical 3DMMs such as FLAME. Face tracking & 3D reconstruction are often limited by the representational capacity of PCA-based face models. By lifting NPHMs to a first-class reconstruction primitive, we enable more accurate geometry, richer expressions, and finer animation control. Pix2NPHM obtains fast and reliable NPHM reconstructions on real-world data. Inference-time optimization against surface normals and canonical point maps can further increase fidelity. Key to successful and generalized training of our ViT-based network are: (1) large-scale registration of existing 3D head datasets, and (2) self-supervised training on vast in-the-wild 2D video datasets using pseudo ground-truth surface normals. Finally, we show that geometry-aware pretraining on pixel-aligned reconstruction tasks significantly outperforms generic visual pretraining (e.g., DINO-style features) in terms of generalization. 🌍 🎥 Great work by Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Zhe Chen
0:17

📢Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image📢 We directly regress neural parametric head models (NPHMs) from a single image — fast, stable, and significantly more expressive than classical 3DMMs such as FLAME. Face tracking & 3D reconstruction are often limited by the representational capacity of PCA-based face models. By lifting NPHMs to a first-class reconstruction primitive, we enable more accurate geometry, richer expressions, and finer animation control. Pix2NPHM obtains fast and reliable NPHM reconstructions on real-world data. Inference-time optimization against surface normals and canonical point maps can further increase fidelity. Key to successful and generalized training of our ViT-based network are: (1) large-scale registration of existing 3D head datasets, and (2) self-supervised training on vast in-the-wild 2D video datasets using pseudo ground-truth surface normals. Finally, we show that geometry-aware pretraining on pixel-aligned reconstruction tasks significantly outperforms generic visual pretraining (e.g., DINO-style features) in terms of generalization. 🌍 🎥 Great work by Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Zhe Chen

Matthias Niessner

37,993 Aufrufe • vor 10 Monaten

"Spann3R: 3D Reconstruction with Spatial Memory" In a nutshell: DUSt3R strikes again! Paper: Project: Method ⬇️
0:14

"Spann3R: 3D Reconstruction with Spatial Memory" In a nutshell: DUSt3R strikes again! Paper: Project: Method ⬇️

MrNeRF

52,560 Aufrufe • vor 2 Jahren

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited): – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.
0:13

Human Hair Reconstruction with Strand-Aligned 3D Gaussians Contributions (cited): – We propose a new 3D line lifting scheme that uses a modified 3DGS reconstruction technique to lift 2D orientation maps into a 3D field while also providing refinement of the camera parameters; – We introduce a dual representation of hair strand polylines and 3D Gaussians to achieve differentiable rasterization of hair strands and leverage photometric constraints for strand-based hair reconstruction; – Based on these components, we propose a coarse-to-fine optimization method for prior-guided hair reconstruction that leverages both latent and explicit representations of the hairstyle.

MrNeRF

106,724 Aufrufe • vor 2 Jahren

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.
0:19

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

MrNeRF

21,397 Aufrufe • vor 1 Jahr

Facial reconstruction of a 6,500-year-old EHG man from Murzikha, Tatarstan, belonging to the Garino-Bor culture. Anthropologists classified Murzikha EHGs as a mixture of ancient Sublaponoid type and Subural type. Reconstruction completed in collaboration with Alexey Nechvaloda.
0:10

Facial reconstruction of a 6,500-year-old EHG man from Murzikha, Tatarstan, belonging to the Garino-Bor culture. Anthropologists classified Murzikha EHGs as a mixture of ancient Sublaponoid type and Subural type. Reconstruction completed in collaboration with Alexey Nechvaloda.

Ancestral Whispers

42,497 Aufrufe • vor 1 Jahr

Scanning large surface with PBR maps? No problem! Still polishing the methodologies and approach but initial tests are very promising. Here is a 130 x 50 cm tabletop, tricky reflective surface especially if we are aiming for smooth reconstruction.
0:18

Scanning large surface with PBR maps? No problem! Still polishing the methodologies and approach but initial tests are very promising. Here is a 130 x 50 cm tabletop, tricky reflective surface especially if we are aiming for smooth reconstruction.

McGavish

18,326 Aufrufe • vor 2 Jahren

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.
0:13

GSTAR: Gaussian Surface Tracking and Reconstruction Contributions: • A new framework for tracking and reconstructing dynamic scenes, combining 3D Gaussians and meshes to effectively manage changes in topology. • A method for Gaussian unbinding and surface re-meshing, allowing for the generation of new surfaces as topologies evolve. • A method for handling large or fast deformations of surfaces between frames using scene flow warping. Abstract (excerpt): However, tracking dynamic surfaces with 3D Gaussians remains challenging due to complex topology changes, such as surfaces appearing, disappearing, or splitting. To address these challenges, we propose GSTAR, a novel method that achieves photo-realistic rendering, accurate surface reconstruction, and reliable 3D tracking for general dynamic scenes with changing topology. Given multi-view captures as input, GSTAR binds Gaussians to mesh faces to represent dynamic objects. For surfaces with consistent topology, GSTAR maintains the mesh topology and tracks the meshes using Gaussians.

MrNeRF

22,698 Aufrufe • vor 1 Jahr

Toenail reconstruction with resin 💅
0:17

Toenail reconstruction with resin 💅

noface

377,471 Aufrufe • vor 3 Monaten

🎉 We just released code, data and model for our #SIGGRAPH2023 work "CT2Hair"!! CT2Hair achieves fully automatic reconstruction of production-ready hair strands from computed tomography (CT) scans!! Code&Data: Project:
0:14

🎉 We just released code, data and model for our #SIGGRAPH2023 work "CT2Hair"!! CT2Hair achieves fully automatic reconstruction of production-ready hair strands from computed tomography (CT) scans!! Code&Data: Project:

Shunsuke Saito

56,138 Aufrufe • vor 3 Jahren

Facial reconstruction of Homo Longi, a Denisovan from Harbin, China Recently confirmed as a Denisovan. He possessed a massive skull measuring 221 mm in length and 164 mm in width, with a cranial capacity of 1,420 cm³. Reconstruction created in collaboration with InterspeciesFace
0:10

Facial reconstruction of Homo Longi, a Denisovan from Harbin, China Recently confirmed as a Denisovan. He possessed a massive skull measuring 221 mm in length and 164 mm in width, with a cranial capacity of 1,420 cm³. Reconstruction created in collaboration with InterspeciesFace

Ancestral Whispers

35,217 Aufrufe • vor 1 Jahr

Reconstruction #b3d
0:11

Reconstruction #b3d

Max Hay

14,083 Aufrufe • vor 2 Monaten