Mip-NeRF 360
PulseAugur coverage of Mip-NeRF 360 — every cluster mentioning Mip-NeRF 360 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New TFD-SfM method recovers camera poses from uncalibrated images
Researchers have developed a novel Track-Free Dense Structure from Motion (TFD-SfM) method that bypasses the need for precise metric initialization and known camera intrinsics. This approach models each pixel match as a…
-
MVLoMa enhances multi-view local feature matching with geometry context
Researchers have developed MVLoMa, a novel local feature matching system designed to extend pairwise matching to multiple views. This system enhances geometric understanding by injecting cross-view context into local de…
-
AI system SplatLab autonomously conducts 3DGS scientific research · 2 sources tracked
SplatLab, an autonomous AI research system, has been developed to conduct scientific discovery in the field of 3D Gaussian Splatting (3DGS). This system can autonomously reproduce published research, propose and impleme…
-
PocketSplat enables mobile Gaussian reconstruction on iPhones
Researchers have developed PocketSplat, a new framework for creating Gaussian reconstruction assets on mobile devices. This system is designed to operate within the resource constraints of mobile phones and produce asse…
-
RouteBridge framework enhances NeRF and 3D Gaussian Splatting distillation
Researchers have developed RouteBridge, a novel bidirectional framework designed to improve the distillation process between Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS). This system adaptively select…
-
UniQueR framework advances 3D reconstruction with sparse 3D query inference
Researchers have introduced UniQueR, a novel framework for 3D reconstruction from unposed images. Unlike previous feedforward models that produce 2.5D outputs limited to visible surfaces, UniQueR treats reconstruction a…
-
New 3DGART framework accelerates ray-traced Gaussian rendering training
Researchers have developed 3DGART, a new training framework for ray-traced Gaussian rendering that significantly speeds up the process. By reorganizing backward propagation from a pixel-centric approach to a primitive-c…
-
GenRec model separates reconstruction and generation for novel view synthesis
Researchers have introduced GenRec, a novel multi-view flow matching model designed to improve generative novel view synthesis. This model explicitly separates reconstruction from generation, addressing limitations in e…
-
VoroTracing achieves real-time ray tracing speeds, outperforming rasterization
Researchers have developed VoroTracing, a novel differentiable Voronoi ray tracing technique that achieves real-time rendering speeds, surpassing traditional rasterization methods. This new approach analyzes factors lik…
-
SplatGuide uses 3D Gaussians for pose-free novel view synthesis · arXiv
Researchers have introduced SplatGuide, a novel method for generating photorealistic novel views from unposed images. This approach leverages geometric priors from 3D Gaussians, reusing a single 3D Gaussian Splatting (3…
-
New method enhances 3D Gaussian Splatting compression against packet loss
Researchers have developed a new method to improve the robustness of 3D Gaussian Splatting (3DGS) and its compression schemes against packet loss during network streaming. The proposed framework uses atomic packaging to…
-
New framework enhances spike-based NeRFs with adaptive time-step training
Researchers have developed a new framework called PATA (Pretraining-based Adaptive Time-step Adjustment) to improve the efficiency of spike-based Neural Radiance Fields (NeRFs). This method allows for scene-specific ada…
-
New method improves sparse-view neural reconstruction with selective depth supervision
Researchers have developed a method to improve sparse-view neural reconstruction in outdoor driving scenes by selectively applying monocular depth supervision. The technique uses Depth Anything V2 to provide dense geome…
-
SkipGS method accelerates 3D Gaussian Splatting training by 23%
Researchers have developed SkipGS, a new method to significantly speed up the training of 3D Gaussian Splatting (3DGS) models. The technique focuses on optimizing the backward pass, which is a major bottleneck in the po…
-
3D Gaussian Splatting advances scene representation and editing
Researchers are advancing 3D Gaussian Splatting (3DGS) with new methods for improved scene representation, editing, and compression. Innovations include Skew-Normal Splatting for better modeling of asymmetric structures…