arXiv AI
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
2d ago
MeshOctave generates meshes via cascading resolution transitions
arXiv:2609.38985v1 Announce Type: new Abstract: Generating compact, artist-style meshes with explicit topology typically relies on autoregressive models which incur prohibitive sequential per-token c...
arXiv AI
Sep 16
KaiNinja: Extending Native 3D Generators to the Part Level
KaiNinja extends the native 3D generator TRELLIS.2 to produce part-level meshes by introducing a dual‑volume representation that overcomes the single‑sheet limitation of the O‑Voxel grid. It maintains TRELLIS.2’s speed and quality while eliminating the need for external segmentation, and is trained on diverse data including CAD models and assets created by an LLM‑driven agent. The method improves whole‑object fidelity and outperforms other part‑generation pipelines, reducing Chamfer distance by 40% and increasing strict part F‑score by 16%.
arXiv AI
Sep 15
Kaininja: Extending Native 3D Generators to the Part Level
arXiv:2609.15659v1 Announce Type: cross Abstract: Native 3D generators turn one image into a single mesh. TRELLIS.2 and its peers deliver high-fidelity non-watertight geometry with materials, but the...
arXiv AI
Aug 11
P2Voxel: Pyramid Pivot Voxelization for 3D Mesh Tokenization
arXiv:2608. 07549v1 Announce Type: cross Abstract: Triangle meshes provide explicit and accurate surface geometry, yet their irregular topology connectivity makes 3D mesh tokenization a geometric sampling problem: how to sample and organize geometric evidence into compact, structured and learnable tokens.
arXiv AI
Aug 6
CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding
arXiv:2608. 04515v1 Announce Type: cross Abstract: Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices.
arXiv Computer Vision
Sep 17
Generalizable Neural Reconstruction of High-Fidelity Surfaces via Sparse Volumetric Representations
The paper introduces SVRecon, a generalizable neural surface reconstruction framework that uses sparse volumetric representations to achieve high-resolution 3D reconstruction. It employs a two-stage architecture: first predicting occupied voxels with an occupancy network, then rendering only within those regions using specialized sparse algorithms. This approach allows reconstruction at resolutions up to 512³ on 32 GB hardware, producing smoother and more precise surfaces, especially in sparse-view scenarios.