Keep on to blur preview images; turn off to show them clearly
RT @janusch_patas: Mip 2D filter arrived in LichtFeld Studio. Many thanks to @fhahlbohm! Try the latest portable nightly builds for Window…
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
Mip 2D filter arrived in LichtFeld Studio. Many thanks to @fhahlbohm! Try the latest portable nightly builds for Windows at https://t.co/fU7sWxK55G Note: pre-alpha dev builds! Expect unexpected behaviour
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
RT @JDihlmann: MatSpray: Fusing 2D Material World Knowledge on 3D Geometry Super fast materials for every 3D Gaussian Splatting scene from…
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
![MatSpray: Fusing 2D Material World Knowledge on 3D Geometry
Contributions:
• World Material Fusion: A plug-and-play pipeline that, to our knowledge, is the first to fuse swappable diffusion-based 2D PBR priors ("world material knowledge") with 3D Gaussian material optimization. It uses Gaussian ray tracing and PBR consistent supervision to obtain relightable assets.
• Neural Merger: A softmax neural merger that aggregates per-Gaussian, multi-view material estimates, suppresses baked-in lighting, and enforces cross-view consistency while stabilizing joint environment map optimization.
• Faster Reconstruction: A simple projection and optimization scheme that reconstructs high-quality relightable 3D materials with 3.5× less per-scene optimization time than IRGS [9].](/_next/image?url=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2003360301333512198%2Fimg%2FQkqLL_37pcs3nDBx.jpg&w=3840&q=75 "MatSpray: Fusing 2D Material World Knowledge on 3D Geometry
Contributions:
• World Material Fusion: A plug-and-play pipeline that, to our knowledge, is the first to fuse swappable diffusion-based 2D PBR priors (\"world material knowledge\") with 3D Gaussian material optimization. It uses Gaussian ray tracing and PBR consistent supervision to obtain relightable assets.
• Neural Merger: A softmax neural merger that aggregates per-Gaussian, multi-view material estimates, suppresses baked-in lighting, and enforces cross-view consistency while stabilizing joint environment map optimization.
• Faster Reconstruction: A simple projection and optimization scheme that reconstructs high-quality relightable 3D materials with 3.5× less per-scene optimization time than IRGS [9].")
MatSpray: Fusing 2D Material World Knowledge on 3D Geometry Contributions: • World Material Fusion: A plug-and-play pipeline that, to our knowledge, is the first to fuse swappable diffusion-based 2D PBR priors ("world material knowledge") with 3D Gaussian material optimization. It uses Gaussian ray tracing and PBR consistent supervision to obtain relightable assets. • Neural Merger: A softmax neural merger that aggregates per-Gaussian, multi-view material estimates, suppresses baked-in lighting, and enforces cross-view consistency while stabilizing joint environment map optimization. • Faster Reconstruction: A simple projection and optimization scheme that reconstructs high-quality relightable 3D materials with 3.5× less per-scene optimization time than IRGS [9].
Paper: https://t.co/ZIQjEjjtUM Project: https://t.co/SMjrucR9r1
Paper: https://t.co/FlrWYN4O4m Project: https://t.co/SKQEjXumsa Code: https://t.co/rS4piJoNtz: Fusing 2D Material World Knowledge on 3D Geometry
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
WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion Contributions: - WorldWarp: A novel framework for long-range novel view extrapolation that generates video chunk-by-chunk using an autoregressive inference pipeline. - Spatio-Temporal Diffusion (ST-Diff): A non-causal diffusion model that leverages bidirectional attention conditioned on forward-warped images as a dense geometric prior. - An online 3D geometric cache mechanism: Uses test-time optimized 3DGS [25] to provide high-fidelity warped priors while preventing the irreversible error propagation of static 3D representations. - State-of-the-art performance on challenging view extrapolation benchmarks, demonstrating significantly improved geometric consistency and image quality over existing methods.
Paper: https://t.co/FlrWYN4O4m Project: https://t.co/SKQEjXumsa Code: https://t.co/rS4piJoNtz: Fusing 2D Material World Knowledge on 3D Geometry