arXiv Machine Learning
When 3D Gaussian Splatting Recovers Real Surfaces
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 4
Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting
arXiv:2606. 05124v1 Announce Type: cross Abstract: After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation.
arXiv Computer Vision
5d ago
RGS: Reflection-aware Gaussian Splatting via Learning Geometry Continuity for Reflective Objects
The paper introduces Reflection-aware Gaussian Splatting (RGS), a physically-based deferred rendering framework that improves novel view synthesis for reflective objects. RGS leverages a powerful 3D foundation model to provide a strong geometric prior and employs cross-view shape consistency regularization to prevent surface collapse and reduce geometric hollows. Additionally, a reflection-aware densification strategy captures specular variations across views, resulting in higher-quality renderings of reflective objects.
arXiv Computer Vision
Sep 4
Camera Splatting for Continuous View Optimization
The paper introduces Camera Splatting, a novel framework for optimizing camera viewpoints in novel view synthesis. Each camera is represented as a 3D Gaussian (camera splat), and virtual point cameras are positioned near the surface to sample the distribution of these splats. By continuously refining the camera splats to match desired target distributions observed from the point cameras, the method achieves better capture of complex view‑dependent effects such as metallic reflections and detailed textures compared to the Farthest View Sampling approach.
arXiv Computer Vision
5d ago
Printing the Underdetermined: Materializing Multi-solutionness in Figurative Paintings
The paper challenges the common assumption that figurative paintings represent a single, recoverable 3D scene. It introduces the concept of multi-solutionness, highlighting how unobserved content and ambiguous visual cues allow multiple plausible 3D configurations. The authors present a workflow that generates multiple camera-orbit video sequences from a single painting, reconstructs each with 3D Gaussian Splatting, and fabricates the resulting point-based Gaussian scenes as physical artifacts via DreamPrinting, thereby making the non-uniqueness of interpretations explicit and inspectable.
arXiv Computer Vision
1d ago
LiteTex-GS: Fast and Lightweight Texturing for Gaussian Splatting
arXiv:2609.23380v1 Announce Type: new Abstract: Gaussian Splatting has enabled real-time novel view synthesis, but its tightly coupled geometry and appearance representation often require a large num...
arXiv AI
Jul 1
Intrinsic decomposition and editing of 3D Gaussian splats
arXiv:2606. 31637v1 Announce Type: cross Abstract: Intrinsic decomposition which expresses image colors as the product of diffuse albedo and shading, possibly augmented with view-dependent residuals has a long history in image editing as it enables the modification of object colors and textures without altering lighting.