ObjectSplat: Improving Mesh Fidelity and Interactivity for 3D Scenes via Object-Level Mesh Splatting
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial IntelligenceMachine Learning
AI summaryⓘ
The authors improve a method that creates 3D scenes from photos by breaking the scene into separate objects before rebuilding it. This helps fix areas that were not directly seen in the photos, making the 3D models look better and more accurate. Their approach also allows users to edit or interact with individual objects in the scene. Overall, their method produces higher-quality 3D reconstructions that can be easily modified.
3D reconstructionsplattingmesh fidelitynovel-view synthesisinstance segmentationinpaintingmesh exportobject-level structure
Authors
Minhas Kamal, Hiranya Garbha Kumar, Mahedi Kamal, Balakrishnan Prabhakaran
Abstract
Splatting-based algorithms reconstruct photorealistic, real-time-renderable, and mesh-exportable 3D scenes from regular images, but they represent a scene as a single monolithic field. Therefore, the reconstruction has no object-level structure, leaving it infeasible for downstream editing or interaction. Moreover, regions that are never directly observed in the input scans are contaminated by the surrounding texture and left uncorrected, capping both mesh fidelity and novel-view synthesis. We propose a decompose-before-reconstruct approach: we segment the instances out of every frame, consider the remaining as background and inpaint it, reconstruct each instance and the background independently with mesh splatting, and compose them into a single scene. Our method significantly improves mesh fidelity (over a 5\% gain in F-score) and novel-view synthesis, while supporting object-wise modifiability and interactivity. The code will be made publicly available.